Compare commits
197 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| c0ea4a2d00 | |||
| 86ead8e5a0 | |||
| 425805ab23 | |||
| 98252e06c3 | |||
| 20bde939eb | |||
| 8be7965ed1 | |||
| 4a125590b9 | |||
| 76d473d731 | |||
| 7653c2f7ad | |||
| 90844fe9ad | |||
| 37c27c0213 | |||
| 0cf8108ff0 | |||
| cc561277c9 | |||
| 4b87868122 | |||
| 948d118926 | |||
| 4b7b9fd5b6 | |||
| 65bd6d71d0 | |||
| 00ec6888c5 | |||
| 6e4824cb74 | |||
| f1b55de6bc | |||
| 6fc00b8de1 | |||
| 427db102d8 | |||
| e46f9b9a21 | |||
| 10a6c6255a | |||
| 77d184efd8 | |||
| 1ca7f562ef | |||
| 3bccbf883d | |||
| b788b553c0 | |||
| 4b46c4baf8 | |||
| 8e744c076d | |||
| cc494c6937 | |||
| e2fa96318f | |||
| 416c3c4758 | |||
| 1c7ef28c5d | |||
| 1a0218799b | |||
| 048f28a671 | |||
| b818f07c80 | |||
| 06507ed8bf | |||
| 044a9a86d6 | |||
| 62d4ca6367 | |||
| 871f788f0b | |||
| 18f5596b01 | |||
| afb8b367ee | |||
| 58b14ae769 | |||
| 23c5bac666 | |||
| d925dc5cd3 | |||
| b8ddd2f8d2 | |||
| 301ca9d186 | |||
| 3bd8a52ea2 | |||
| 789e8c6236 | |||
| a3ea215a1c | |||
| c6e0b80bec | |||
| e86e1b9f13 | |||
| 46a9a30af0 | |||
| bdfa3ba1e0 | |||
| 8295279ec9 | |||
| 152ee15b06 | |||
| a75e8b9297 | |||
| ee664f83fb | |||
| 91ef089aa7 | |||
| 925864ddca | |||
| 57db4c7c82 | |||
| 35752c9092 | |||
| 9b9882c4d6 | |||
| 6a77533795 | |||
| 69053bfb08 | |||
| f1cf5d0e76 | |||
| c547ad1acc | |||
| 1625896e30 | |||
| 470f08d893 | |||
| a57766ed7e | |||
| 76f202f7f1 | |||
| 33484b236a | |||
| 6927e7643f | |||
| aeb50c21d2 | |||
| 45e41338dc | |||
| f0d3563029 | |||
| 12a35f9b30 | |||
| 4136033bf0 | |||
| 48331f6e91 | |||
| cafc0e4523 | |||
| a2c9915908 | |||
| c3124b08bd | |||
| 4faba2ec08 | |||
| 2f3c22000c | |||
| aca12858c1 | |||
| ae524bb94e | |||
| 5af4dbcb25 | |||
| 94a090da77 | |||
| 3fd8b32724 | |||
| 7f20c903ef | |||
| 8fcc223ef1 | |||
| ce050b542a | |||
| 114b69a8c2 | |||
| f6591d10fc | |||
| c26c376e2e | |||
| 627a8579de | |||
| f041f28d9f | |||
| 7dec570ce6 | |||
| c7d3ec57c3 | |||
| 11a49eb7fd | |||
| 527fb666d0 | |||
| 07bdee94b0 | |||
| b7e33af669 | |||
| 965647940b | |||
| 2f5e2a0fcd | |||
| c9bb2b6807 | |||
| c03ce8cdb2 | |||
| 0b8f967eb5 | |||
| 315d85c443 | |||
| f8f95085fc | |||
| 7bd9d20091 | |||
| c61afb2c33 | |||
| dd5603bdd0 | |||
| 0c3ee6f484 | |||
| 6f510d5a2d | |||
| 2014a93c1b | |||
| 3be93be35a | |||
| 4cac9fbe9b | |||
| bcdbf9d178 | |||
| fc1365dfec | |||
| 52e8e535ff | |||
| ef5528dcef | |||
| ea2dad0c08 | |||
| 8e26e3aaa7 | |||
| 2a5296d7e7 | |||
| a052b2fbe0 | |||
| a384b222f1 | |||
| 326adb1858 | |||
| e330a611d0 | |||
| 15dd1a8471 | |||
| 2ee6bfc7ea | |||
| 248619d91e | |||
| 8984d4da70 | |||
| 0596206e17 | |||
| 26963a8464 | |||
| 1e7f2275d3 | |||
| 88368f7f76 | |||
| 7fbcf5c593 | |||
| 01c04c20ce | |||
| cfcce57e35 | |||
| 10297ede37 | |||
| 78bd5b5904 | |||
| 9153b1f7f0 | |||
| f9b4975093 | |||
| 47595818b4 | |||
| bad369548b | |||
| 7ea8b17fd2 | |||
| cc5e879ea9 | |||
| 7490462c67 | |||
| c25e1b0e21 | |||
| a10f8e628e | |||
| 1018ea17d9 | |||
| 7c1967b728 | |||
| 06b0fced38 | |||
| 341839fe5e | |||
| 28d4bced0c | |||
| d22175310a | |||
| 7755f5a1ed | |||
| cee6d6d4e1 | |||
| 0497fbbbad | |||
| 57795ee487 | |||
| a4bd1d7178 | |||
| d94e9ca4bc | |||
| 82c6915c42 | |||
| d71945b7b9 | |||
| 91f36e0d5a | |||
| 1e69c55947 | |||
| 9b748db4d4 | |||
| eeae47ddec | |||
| be500e1a2b | |||
| 45d3ac8cf0 | |||
| 4df4673628 | |||
| 9642020887 | |||
| 89dec45062 | |||
| 34457f9775 | |||
| b0fe1a014a | |||
| 1d9bd15a70 | |||
| b50a534454 | |||
| 80de3b6743 | |||
| 8b4280d5dd | |||
| 93629ff440 | |||
| c4e10bee5e | |||
| 084171395d | |||
| 958b195e79 | |||
| c5ef1ec50c | |||
| b4e0067a27 | |||
| 6188003897 | |||
| ef897f660d | |||
| 6cb9feacab | |||
| 76c0e91500 | |||
| 78077fa8c7 | |||
| 242846aa9c | |||
| 868613ac49 | |||
| 14b3031e63 | |||
| 1d7df13c94 | |||
| 48a303d498 |
@@ -3,21 +3,10 @@ WORKDIR=/workdir
|
||||
DATABASE_URL=sqlite:///./app/database.db
|
||||
REDIS_URL=redis://redis:6379/0
|
||||
EXTERNAL_HOSTNAME=docuelevate.example.com
|
||||
# PUBLIC_BASE_URL=https://docuelevate.example.com # Full URL with scheme; required when X-Forwarded-Proto is not forwarded by your proxy
|
||||
GOTENBERG_URL=http://gotenberg:3000
|
||||
ALLOW_FILE_DELETE=true # Allow deletion of file records
|
||||
COMPLIANCE_ENABLED=true # Enable compliance templates dashboard (GDPR, HIPAA, SOC 2)
|
||||
|
||||
# **Database Connection Pool** (PostgreSQL / MySQL only; ignored for SQLite)
|
||||
# DB_POOL_SIZE=10 # Persistent connections per worker (default: 10)
|
||||
# DB_MAX_OVERFLOW=20 # Extra connections under burst (default: 20)
|
||||
# DB_POOL_TIMEOUT=30 # Seconds to wait for a pool connection (default: 30)
|
||||
# DB_POOL_RECYCLE=1800 # Recycle connections after N seconds (default: 1800)
|
||||
|
||||
# **Per-User Upload Rate Limiting** (health-aware, Redis-backed)
|
||||
# UPLOAD_RATE_LIMIT_PER_USER=20 # Max uploads per user per window (default: 20)
|
||||
# UPLOAD_RATE_LIMIT_WINDOW=60 # Sliding window in seconds (default: 60)
|
||||
|
||||
# **System Reset / Factory Reset**
|
||||
# FACTORY_RESET_ON_STARTUP=false # Wipe all user data on every startup (demo/testing only)
|
||||
# ENABLE_FACTORY_RESET=false # Show the System Reset page in admin UI
|
||||
@@ -636,26 +625,9 @@ EMBEDDING_MAX_TOKENS=8000
|
||||
# Profiling is only active when SENTRY_TRACES_SAMPLE_RATE > 0. Default: 0.0 (disabled).
|
||||
# SENTRY_PROFILES_SAMPLE_RATE=0.0
|
||||
#
|
||||
# Attach PII (IP addresses, user agents) to Sentry events.
|
||||
# Disable (default) to stay GDPR/CCPA compliant.
|
||||
# SENTRY_SEND_DEFAULT_PII=false
|
||||
#
|
||||
# --- Browser (JavaScript) SDK ---
|
||||
# The same DSN is reused for the Sentry Browser SDK which is injected into
|
||||
# every rendered page. The DSN is a *public* key and is intentionally
|
||||
# embedded in client-side code.
|
||||
#
|
||||
# Fraction of browser navigations captured for client-side performance tracing.
|
||||
# 0.0 (default) disables browser tracing; 1.0 captures every navigation.
|
||||
# SENTRY_JS_TRACES_SAMPLE_RATE=0.0
|
||||
#
|
||||
# Fraction of browser sessions recorded by Sentry Session Replay.
|
||||
# 0.0 (default) disables session recording; 1.0 records every session.
|
||||
# SENTRY_JS_REPLAY_SESSION_SAMPLE_RATE=0.0
|
||||
#
|
||||
# Fraction of error sessions recorded by Sentry Session Replay.
|
||||
# Defaults to 0.1 (10 %) so errors are captured with replay context.
|
||||
# SENTRY_JS_REPLAY_ON_ERROR_SAMPLE_RATE=0.1
|
||||
# Attach PII (IP addresses, user agents) to Sentry events.
|
||||
# Disable (default) to stay GDPR/CCPA compliant.
|
||||
# SENTRY_SEND_DEFAULT_PII=false
|
||||
|
||||
# **Mobile App – Push Notifications**
|
||||
# Push notifications are delivered via Expo's push notification service
|
||||
|
||||
@@ -100,7 +100,7 @@ jobs:
|
||||
python-version: "3.11"
|
||||
cache: 'pip'
|
||||
- run: pip install pip-audit>=2.7.0
|
||||
- run: pip-audit -r requirements.txt --desc on
|
||||
- run: pip-audit -r requirements.txt --desc on --ignore-vuln CVE-2026-4539
|
||||
|
||||
run-tests:
|
||||
name: Execute All Tests (Quick + Integration)
|
||||
|
||||
@@ -200,3 +200,5 @@ cython_debug/
|
||||
# Build metadata files - generated at build time
|
||||
GIT_SHA
|
||||
RUNTIME_INFO
|
||||
node_modules
|
||||
frontend/node_modules
|
||||
|
||||
@@ -1,3 +0,0 @@
|
||||
[submodule "vendor/embed-pdf-viewer"]
|
||||
path = vendor/embed-pdf-viewer
|
||||
url = https://github.com/embedpdf/embed-pdf-viewer.git
|
||||
+4
-8
@@ -1,8 +1,4 @@
|
||||
## 2024-05-24 - SSRF in WebDAV connection test
|
||||
**Vulnerability:** The `_test_webdav_connection` function had a custom SSRF check that failed to resolve DNS names, allowing attackers to bypass the check by providing a domain that resolves to an internal IP (e.g., `127.0.0.1`).
|
||||
**Learning:** DNS resolution is required for robust SSRF protection when validating URLs provided by users.
|
||||
**Prevention:** Use a centralized `is_private_ip` function (now in `app/utils/network.py`) that resolves the hostname to its IPs and checks if any are private.
|
||||
## 2026-03-22 - B310: urllib.request.urlopen replaced with httpx
|
||||
**Vulnerability:** The `_test_webdav_connection` function used `urllib.request.urlopen`, which natively supports dangerous schemes like `file://` or `ftp://` and follows redirects by default, potentially allowing SSRF bypasses or Local File Inclusion.
|
||||
**Learning:** `urllib.request` should be avoided for user-supplied URLs. Even when URL schemes are manually validated, `urllib`'s default redirect following behavior can bypass SSRF protections (e.g. redirecting to `127.0.0.1`).
|
||||
**Prevention:** Use a modern, safer HTTP client like `httpx` with `follow_redirects=False` when testing user-provided URLs.
|
||||
## 2026-06-01 - [Fix XSS in status_dashboard.html]
|
||||
**Vulnerability:** A Cross-Site Scripting (XSS) vulnerability existed in `frontend/templates/status_dashboard.html` where untrusted configuration settings (`value`), external service messages (`data.message`), and token expirations (`data.token_info.expires_in_human`) were injected directly into the DOM via `.innerHTML` without sanitization.
|
||||
**Learning:** Even internal or admin-focused dashboards can be vulnerable if they display external or user-configurable data without escaping. Constructing HTML strings dynamically from unvalidated sources is a common vector for DOM-based XSS.
|
||||
**Prevention:** Always use a sanitization function like `escapeHtml` to escape dangerous characters (`<`, `>`, `&`, `"`, `'`) before assigning dynamic content to `.innerHTML`, or prefer `.textContent` when only plaintext is intended.
|
||||
|
||||
+1
-1
@@ -1 +1 @@
|
||||
2026-03-22T17:46:27Z
|
||||
2026-06-01T03:41:15Z
|
||||
|
||||
+615
@@ -10,6 +10,621 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
<!-- version list -->
|
||||
|
||||
## v0.173.4 (2026-06-01)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- Address status dashboard xss review nits
|
||||
([`425805a`](https://github.com/christianlouis/DocuElevate/commit/425805ab23882944aee0cb02b5e497bc536549c0))
|
||||
|
||||
### Build System
|
||||
|
||||
- **deps**: Update redis requirement from >=4.5.0 to >=8.0.0
|
||||
([#904](https://github.com/christianlouis/DocuElevate/pull/904),
|
||||
[`20bde93`](https://github.com/christianlouis/DocuElevate/commit/20bde939eb96ec8e6700b206e046388b6b891e38))
|
||||
|
||||
- **deps-dev**: Update pytest-asyncio requirement
|
||||
([#903](https://github.com/christianlouis/DocuElevate/pull/903),
|
||||
[`4a12559`](https://github.com/christianlouis/DocuElevate/commit/4a125590b9b6cb2f07bae187a9bff708dd92a5c3))
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`98252e0`](https://github.com/christianlouis/DocuElevate/commit/98252e06c30bba78520a8460d55f508dbf2bdd47))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`8be7965`](https://github.com/christianlouis/DocuElevate/commit/8be7965ed1892978092c3f5e02e6252918c237fd))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Build System
|
||||
|
||||
- **deps**: Update redis requirement from >=4.5.0 to >=8.0.0
|
||||
([#904](https://github.com/christianlouis/DocuElevate/pull/904),
|
||||
[`20bde93`](https://github.com/christianlouis/DocuElevate/commit/20bde939eb96ec8e6700b206e046388b6b891e38))
|
||||
|
||||
- **deps-dev**: Update pytest-asyncio requirement
|
||||
([#903](https://github.com/christianlouis/DocuElevate/pull/903),
|
||||
[`4a12559`](https://github.com/christianlouis/DocuElevate/commit/4a125590b9b6cb2f07bae187a9bff708dd92a5c3))
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`8be7965`](https://github.com/christianlouis/DocuElevate/commit/8be7965ed1892978092c3f5e02e6252918c237fd))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Build System
|
||||
|
||||
- **deps-dev**: Update pytest-asyncio requirement
|
||||
([#903](https://github.com/christianlouis/DocuElevate/pull/903),
|
||||
[`4a12559`](https://github.com/christianlouis/DocuElevate/commit/4a125590b9b6cb2f07bae187a9bff708dd92a5c3))
|
||||
|
||||
|
||||
## v0.173.3 (2026-05-31)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- Preserve falsy values in escapeHtml
|
||||
([`37c27c0`](https://github.com/christianlouis/DocuElevate/commit/37c27c02139ae4a462e1705bda9360b23eb835b3))
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`cc56127`](https://github.com/christianlouis/DocuElevate/commit/cc561277c9d7d0177b4ac63921637659abb66fba))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`948d118`](https://github.com/christianlouis/DocuElevate/commit/948d118926be042cc3c2a68f58241cc2fcfa23ef))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`65bd6d7`](https://github.com/christianlouis/DocuElevate/commit/65bd6d71d00ff7078a05ce12b00f228405e2ec1e))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`948d118`](https://github.com/christianlouis/DocuElevate/commit/948d118926be042cc3c2a68f58241cc2fcfa23ef))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`65bd6d7`](https://github.com/christianlouis/DocuElevate/commit/65bd6d71d00ff7078a05ce12b00f228405e2ec1e))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`65bd6d7`](https://github.com/christianlouis/DocuElevate/commit/65bd6d71d00ff7078a05ce12b00f228405e2ec1e))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
|
||||
## v0.173.2 (2026-05-23)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- Resolve dependabot npm alerts
|
||||
([`6fc00b8`](https://github.com/christianlouis/DocuElevate/commit/6fc00b8de10b50b4b2f92f6fadbcf7ebbee7136f))
|
||||
|
||||
### Documentation
|
||||
|
||||
- Extend product roadmap and milestones
|
||||
([`e46f9b9`](https://github.com/christianlouis/DocuElevate/commit/e46f9b9a21e5838f883eca4370445e0f1b57e6c9))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`427db10`](https://github.com/christianlouis/DocuElevate/commit/427db102d85fa676dcf01118fd3757fb300b979d))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Documentation
|
||||
|
||||
- Extend product roadmap and milestones
|
||||
([`e46f9b9`](https://github.com/christianlouis/DocuElevate/commit/e46f9b9a21e5838f883eca4370445e0f1b57e6c9))
|
||||
|
||||
|
||||
## v0.173.1 (2026-05-22)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- Register Evernote task settings
|
||||
([`1ca7f56`](https://github.com/christianlouis/DocuElevate/commit/1ca7f562ef284d2fcceca84b38661abe9038912a))
|
||||
|
||||
|
||||
## v0.173.0 (2026-05-22)
|
||||
|
||||
### Code Style
|
||||
|
||||
- Apply ruff auto-fix ([#862](https://github.com/christianlouis/DocuElevate/pull/862),
|
||||
[`4b46c4b`](https://github.com/christianlouis/DocuElevate/commit/4b46c4baf890f3179ac060569ce2e076cf0551b0))
|
||||
|
||||
### Features
|
||||
|
||||
- **storage**: Add Evernote destination
|
||||
([#862](https://github.com/christianlouis/DocuElevate/pull/862),
|
||||
[`4b46c4b`](https://github.com/christianlouis/DocuElevate/commit/4b46c4baf890f3179ac060569ce2e076cf0551b0))
|
||||
|
||||
|
||||
## v0.172.12 (2026-05-17)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- Validate webhook targets before delivery
|
||||
([#846](https://github.com/christianlouis/DocuElevate/pull/846),
|
||||
[`e2fa963`](https://github.com/christianlouis/DocuElevate/commit/e2fa96318f5bd45607baa0fe08a0bf14e1ca83d4))
|
||||
|
||||
### Testing
|
||||
|
||||
- Cover webhook SSRF validation ([#846](https://github.com/christianlouis/DocuElevate/pull/846),
|
||||
[`e2fa963`](https://github.com/christianlouis/DocuElevate/commit/e2fa96318f5bd45607baa0fe08a0bf14e1ca83d4))
|
||||
|
||||
|
||||
## v0.172.11 (2026-05-17)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- Escape search result template values
|
||||
([#853](https://github.com/christianlouis/DocuElevate/pull/853),
|
||||
[`1a02187`](https://github.com/christianlouis/DocuElevate/commit/1a0218799b9a1eb4154e2f4fbb2572cb3922106a))
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`048f28a`](https://github.com/christianlouis/DocuElevate/commit/048f28a6717fa7f5cf4b235f9142e625e80e5d59))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
|
||||
## v0.172.10 (2026-05-17)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- **url-upload**: Handle unsafe redirects as client errors
|
||||
([`871f788`](https://github.com/christianlouis/DocuElevate/commit/871f788f0bd782ba8ad3a7d70e5cd4ccd24f749b))
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`58b14ae`](https://github.com/christianlouis/DocuElevate/commit/58b14ae769b85e25290126256de936743609af06))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
|
||||
## v0.172.9 (2026-04-07)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- **api**: Resolve merge conflicts, add type safety for endpoint_url in S3 connection test
|
||||
([`57db4c7`](https://github.com/christianlouis/DocuElevate/commit/57db4c7c82f4a8df2e7e5e5505e1d5c01768fc16))
|
||||
|
||||
### Chores
|
||||
|
||||
- **ci**: Ignore CVE-2026-4539 in pip-audit until pygments releases a fix
|
||||
([`6927e76`](https://github.com/christianlouis/DocuElevate/commit/6927e7643f9cbe1664f4a1a093511df5b079ed0a))
|
||||
|
||||
### Code Style
|
||||
|
||||
- Apply ruff auto-fix
|
||||
([`8295279`](https://github.com/christianlouis/DocuElevate/commit/8295279ec93570da4eb0445ede8084d1eb2aba99))
|
||||
|
||||
- Sort imports in test_url_upload.py
|
||||
([`bdfa3ba`](https://github.com/christianlouis/DocuElevate/commit/bdfa3ba1e0a5702414e3b449fbde6a6d3149557a))
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`c6e0b80`](https://github.com/christianlouis/DocuElevate/commit/c6e0b80becab81a75aea4ee78f5aaf8b6ac54854))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`9b9882c`](https://github.com/christianlouis/DocuElevate/commit/9b9882c4d62691d0ddd20444e3b77bfe6eecc8c3))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`69053bf`](https://github.com/christianlouis/DocuElevate/commit/69053bfb08d3e2f12a86878044667ac500888837))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`76f202f`](https://github.com/christianlouis/DocuElevate/commit/76f202f7f1b94e39a4e79cd984770310599405bf))
|
||||
|
||||
### Testing
|
||||
|
||||
- Add coverage for url_upload redirect SSRF bypass prevention hook
|
||||
([`152ee15`](https://github.com/christianlouis/DocuElevate/commit/152ee15b06ebf7beb6216423b4c8d93ec2243165))
|
||||
|
||||
- Add tests for SSRF validation in integrations
|
||||
([`470f08d`](https://github.com/christianlouis/DocuElevate/commit/470f08d89322f2904b78a8b0f820973611486c26))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Chores
|
||||
|
||||
- **ci**: Ignore CVE-2026-4539 in pip-audit until pygments releases a fix
|
||||
([`6927e76`](https://github.com/christianlouis/DocuElevate/commit/6927e7643f9cbe1664f4a1a093511df5b079ed0a))
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`9b9882c`](https://github.com/christianlouis/DocuElevate/commit/9b9882c4d62691d0ddd20444e3b77bfe6eecc8c3))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`69053bf`](https://github.com/christianlouis/DocuElevate/commit/69053bfb08d3e2f12a86878044667ac500888837))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`76f202f`](https://github.com/christianlouis/DocuElevate/commit/76f202f7f1b94e39a4e79cd984770310599405bf))
|
||||
|
||||
### Testing
|
||||
|
||||
- Add tests for SSRF validation in integrations
|
||||
([`470f08d`](https://github.com/christianlouis/DocuElevate/commit/470f08d89322f2904b78a8b0f820973611486c26))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Chores
|
||||
|
||||
- **ci**: Ignore CVE-2026-4539 in pip-audit until pygments releases a fix
|
||||
([`6927e76`](https://github.com/christianlouis/DocuElevate/commit/6927e7643f9cbe1664f4a1a093511df5b079ed0a))
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`69053bf`](https://github.com/christianlouis/DocuElevate/commit/69053bfb08d3e2f12a86878044667ac500888837))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`76f202f`](https://github.com/christianlouis/DocuElevate/commit/76f202f7f1b94e39a4e79cd984770310599405bf))
|
||||
|
||||
### Testing
|
||||
|
||||
- Add tests for SSRF validation in integrations
|
||||
([`470f08d`](https://github.com/christianlouis/DocuElevate/commit/470f08d89322f2904b78a8b0f820973611486c26))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Chores
|
||||
|
||||
- **ci**: Ignore CVE-2026-4539 in pip-audit until pygments releases a fix
|
||||
([`6927e76`](https://github.com/christianlouis/DocuElevate/commit/6927e7643f9cbe1664f4a1a093511df5b079ed0a))
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`76f202f`](https://github.com/christianlouis/DocuElevate/commit/76f202f7f1b94e39a4e79cd984770310599405bf))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Chores
|
||||
|
||||
- **ci**: Ignore CVE-2026-4539 in pip-audit until pygments releases a fix
|
||||
([`6927e76`](https://github.com/christianlouis/DocuElevate/commit/6927e7643f9cbe1664f4a1a093511df5b079ed0a))
|
||||
|
||||
|
||||
## v0.172.8 (2026-03-25)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- **api**: Track env_file_written accurately in save_google_drive_settings
|
||||
([`4136033`](https://github.com/christianlouis/DocuElevate/commit/4136033bf0e580cbabe811084ab47ea0d6af8f9a))
|
||||
|
||||
- **tests**: Add admin override fixture to TestSaveDropboxSettings
|
||||
([`cafc0e4`](https://github.com/christianlouis/DocuElevate/commit/cafc0e45230ffea096664c1947ac20753b63f8e9))
|
||||
|
||||
- **tests**: Restore correct route URLs and fix auth/exception handling broken by d221753
|
||||
([`48331f6`](https://github.com/christianlouis/DocuElevate/commit/48331f6e91e6c0dae31ab3be31f9da1eccd0a549))
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`c3124b0`](https://github.com/christianlouis/DocuElevate/commit/c3124b08bd48faa32e76d21d744c9902214048a7))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
|
||||
## v0.172.7 (2026-03-24)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- **api**: Remove duplicate Depends from AdminUser parameters in dropbox, onedrive, google_drive
|
||||
([`7f20c90`](https://github.com/christianlouis/DocuElevate/commit/7f20c903ef23e138518e715c7c7a0297d3e46ff8))
|
||||
|
||||
- **dockerfile**: Add frontend-builder stage to compile Tailwind CSS
|
||||
([`3fd8b32`](https://github.com/christianlouis/DocuElevate/commit/3fd8b32724e3d390ff723e5b090a5603c3b1fc93))
|
||||
|
||||
- **main**: Replace silent except-pass with exception logging to fix S110
|
||||
([`8fcc223`](https://github.com/christianlouis/DocuElevate/commit/8fcc223ef19cf609d8413fb6091eabfa0b34d4a6))
|
||||
|
||||
|
||||
## v0.172.6 (2026-03-24)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- Resolve multiple test failures in imap_tasks, main lifespan, and API settings endpoints
|
||||
([`f041f28`](https://github.com/christianlouis/DocuElevate/commit/f041f28d9f64011df52506ead4bbc87d0797c20e))
|
||||
|
||||
- Restore all code deleted/truncated by d2217531 Jules SSRF commit
|
||||
([`c7d3ec5`](https://github.com/christianlouis/DocuElevate/commit/c7d3ec57c3aca4faeaa0ad2fdbde3a1f770b86a5))
|
||||
|
||||
- **migrations**: Restore accidentally deleted migration files 038-042
|
||||
([`11a49eb`](https://github.com/christianlouis/DocuElevate/commit/11a49eb7fd2218062922a9b8bf01b9a91572bea7))
|
||||
|
||||
- **tasks**: Add -- end-of-options separator to ocrmypdf command in convert_to_pdfa
|
||||
([`7dec570`](https://github.com/christianlouis/DocuElevate/commit/7dec570ce6ae40b934ad075bc06f4cf1dfd9ff2e))
|
||||
|
||||
### Code Style
|
||||
|
||||
- Apply ruff auto-fix
|
||||
([`627a857`](https://github.com/christianlouis/DocuElevate/commit/627a8579def3a6a9d4f78da6469cfde889154402))
|
||||
|
||||
|
||||
## v0.172.5 (2026-03-23)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- **main**: Suppress S110 ruff warnings with noqa comments for intentional try-except-pass
|
||||
([`0b8f967`](https://github.com/christianlouis/DocuElevate/commit/0b8f967eb5e304155752b4492584d4a7509a454c))
|
||||
|
||||
- **settings**: Move os.path.exists inside try block in update_env_file so exceptions are non-fatal
|
||||
([`c9bb2b6`](https://github.com/christianlouis/DocuElevate/commit/c9bb2b6807b371d04edff12d16f838f411b60514))
|
||||
|
||||
### Testing
|
||||
|
||||
- **google_drive**: Fix exception handling test to expect non-fatal 200 like OneDrive equivalent
|
||||
([`2f5e2a0`](https://github.com/christianlouis/DocuElevate/commit/2f5e2a0fcdd9f9532fc55c6d7ce1675b8be3d3e8))
|
||||
|
||||
- **main,imap**: Fix failing IMAP tests and add coverage for shutdown exception paths
|
||||
([`c03ce8c`](https://github.com/christianlouis/DocuElevate/commit/c03ce8cdb2e7849361ea50db888b7e3080eaafcd))
|
||||
|
||||
|
||||
## v0.172.4 (2026-03-23)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- Resolve failing tests in main
|
||||
([`3be93be`](https://github.com/christianlouis/DocuElevate/commit/3be93be35a1564cb6009c5b7d2229820c2b8fafd))
|
||||
|
||||
- **api/dropbox**: _require_admin bypasses auth when AUTH_ENABLED=False,
|
||||
([`3be93be`](https://github.com/christianlouis/DocuElevate/commit/3be93be35a1564cb6009c5b7d2229820c2b8fafd))
|
||||
|
||||
### Chores
|
||||
|
||||
- Simplify and fix naming for save settings endpoints
|
||||
([`341839f`](https://github.com/christianlouis/DocuElevate/commit/341839fe5edafa3451f89e2bb57092882d8fd6f0))
|
||||
|
||||
- Simplify and fix naming for save settings endpoints
|
||||
([`57795ee`](https://github.com/christianlouis/DocuElevate/commit/57795ee4871bb0bb0727037a889542bf46a8bb9e))
|
||||
|
||||
### Code Style
|
||||
|
||||
- Apply ruff auto-fix
|
||||
([`2014a93`](https://github.com/christianlouis/DocuElevate/commit/2014a93c1ba4f41b8cfb589584be8d39baeaffe1))
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`bcdbf9d`](https://github.com/christianlouis/DocuElevate/commit/bcdbf9d17885ab3f8750d8426c0ee9f181ced736))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Chores
|
||||
|
||||
- Simplify and fix naming for save settings endpoints
|
||||
([`341839f`](https://github.com/christianlouis/DocuElevate/commit/341839fe5edafa3451f89e2bb57092882d8fd6f0))
|
||||
|
||||
- Simplify and fix naming for save settings endpoints
|
||||
([`57795ee`](https://github.com/christianlouis/DocuElevate/commit/57795ee4871bb0bb0727037a889542bf46a8bb9e))
|
||||
|
||||
|
||||
## v0.172.3 (2026-03-23)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- Improve join_url - use walrus op, remove posixpath.normpath
|
||||
([`15dd1a8`](https://github.com/christianlouis/DocuElevate/commit/15dd1a847133aa02aedf65e7fc75d857151cc26e))
|
||||
|
||||
### Code Style
|
||||
|
||||
- Apply ruff auto-fix
|
||||
([`b50a534`](https://github.com/christianlouis/DocuElevate/commit/b50a534454f0432e2ada8140e0090535b7c97051))
|
||||
|
||||
- Apply ruff auto-fix
|
||||
([`326adb1`](https://github.com/christianlouis/DocuElevate/commit/326adb185853e17ac02d30b1bcce33b3a1cf4c5c))
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`248619d`](https://github.com/christianlouis/DocuElevate/commit/248619d91e91aa9c5660267813367e4cd6f5040f))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`26963a8`](https://github.com/christianlouis/DocuElevate/commit/26963a84643c8c5caeb8536ed4dc55302a517adf))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`78bd5b5`](https://github.com/christianlouis/DocuElevate/commit/78bd5b5904d41d77d8df2a0e3978f630be080f0f))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`cc5e879`](https://github.com/christianlouis/DocuElevate/commit/cc5e879ea98507ec5656cce7162a69d385ee00f2))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`0497fbb`](https://github.com/christianlouis/DocuElevate/commit/0497fbbbad71fd728e528498508bbfc7802dab70))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`45d3ac8`](https://github.com/christianlouis/DocuElevate/commit/45d3ac8cf07d39d49930dd6866f76e6015067b08))
|
||||
|
||||
### Testing
|
||||
|
||||
- Add assertions for task enqueuing parameters
|
||||
([`eeae47d`](https://github.com/christianlouis/DocuElevate/commit/eeae47ddec01339421e503ba484157e798750b8a))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`26963a8`](https://github.com/christianlouis/DocuElevate/commit/26963a84643c8c5caeb8536ed4dc55302a517adf))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`78bd5b5`](https://github.com/christianlouis/DocuElevate/commit/78bd5b5904d41d77d8df2a0e3978f630be080f0f))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`cc5e879`](https://github.com/christianlouis/DocuElevate/commit/cc5e879ea98507ec5656cce7162a69d385ee00f2))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`0497fbb`](https://github.com/christianlouis/DocuElevate/commit/0497fbbbad71fd728e528498508bbfc7802dab70))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`45d3ac8`](https://github.com/christianlouis/DocuElevate/commit/45d3ac8cf07d39d49930dd6866f76e6015067b08))
|
||||
|
||||
### Testing
|
||||
|
||||
- Add assertions for task enqueuing parameters
|
||||
([`eeae47d`](https://github.com/christianlouis/DocuElevate/commit/eeae47ddec01339421e503ba484157e798750b8a))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`78bd5b5`](https://github.com/christianlouis/DocuElevate/commit/78bd5b5904d41d77d8df2a0e3978f630be080f0f))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`cc5e879`](https://github.com/christianlouis/DocuElevate/commit/cc5e879ea98507ec5656cce7162a69d385ee00f2))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`0497fbb`](https://github.com/christianlouis/DocuElevate/commit/0497fbbbad71fd728e528498508bbfc7802dab70))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`45d3ac8`](https://github.com/christianlouis/DocuElevate/commit/45d3ac8cf07d39d49930dd6866f76e6015067b08))
|
||||
|
||||
### Testing
|
||||
|
||||
- Add assertions for task enqueuing parameters
|
||||
([`eeae47d`](https://github.com/christianlouis/DocuElevate/commit/eeae47ddec01339421e503ba484157e798750b8a))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`cc5e879`](https://github.com/christianlouis/DocuElevate/commit/cc5e879ea98507ec5656cce7162a69d385ee00f2))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`0497fbb`](https://github.com/christianlouis/DocuElevate/commit/0497fbbbad71fd728e528498508bbfc7802dab70))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`45d3ac8`](https://github.com/christianlouis/DocuElevate/commit/45d3ac8cf07d39d49930dd6866f76e6015067b08))
|
||||
|
||||
### Testing
|
||||
|
||||
- Add assertions for task enqueuing parameters
|
||||
([`eeae47d`](https://github.com/christianlouis/DocuElevate/commit/eeae47ddec01339421e503ba484157e798750b8a))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`0497fbb`](https://github.com/christianlouis/DocuElevate/commit/0497fbbbad71fd728e528498508bbfc7802dab70))
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`45d3ac8`](https://github.com/christianlouis/DocuElevate/commit/45d3ac8cf07d39d49930dd6866f76e6015067b08))
|
||||
|
||||
### Testing
|
||||
|
||||
- Add assertions for task enqueuing parameters
|
||||
([`eeae47d`](https://github.com/christianlouis/DocuElevate/commit/eeae47ddec01339421e503ba484157e798750b8a))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`45d3ac8`](https://github.com/christianlouis/DocuElevate/commit/45d3ac8cf07d39d49930dd6866f76e6015067b08))
|
||||
|
||||
### Testing
|
||||
|
||||
- Add assertions for task enqueuing parameters
|
||||
([`eeae47d`](https://github.com/christianlouis/DocuElevate/commit/eeae47ddec01339421e503ba484157e798750b8a))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
|
||||
## v0.172.2 (2026-03-23)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- Adapt TemplateResponse calls to Starlette 1.0 new-style API
|
||||
([`c4e10be`](https://github.com/christianlouis/DocuElevate/commit/c4e10bee5e096e71a5bc4fac4928f69e5c04f2fb))
|
||||
|
||||
- Update test assertions and lint fixes for Starlette 1.0 TemplateResponse API
|
||||
([`93629ff`](https://github.com/christianlouis/DocuElevate/commit/93629ff44083d43f79fdd49431457023e53d13e4))
|
||||
|
||||
- **build**: Remove --omit=dev from npm ci in Dockerfile frontend-builder stage
|
||||
([`b4e0067`](https://github.com/christianlouis/DocuElevate/commit/b4e0067a27e2fb161349bd38c6d3b3f3bcb86972))
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`0841713`](https://github.com/christianlouis/DocuElevate/commit/084171395d1076c716aa500a516118db49468ff5))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
|
||||
## v0.172.2 (2026-03-23)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- Adapt TemplateResponse calls to Starlette 1.0 new-style API
|
||||
([`c4e10be`](https://github.com/christianlouis/DocuElevate/commit/c4e10bee5e096e71a5bc4fac4928f69e5c04f2fb))
|
||||
|
||||
- Update test assertions and lint fixes for Starlette 1.0 TemplateResponse API
|
||||
([`93629ff`](https://github.com/christianlouis/DocuElevate/commit/93629ff44083d43f79fdd49431457023e53d13e4))
|
||||
|
||||
- **build**: Remove --omit=dev from npm ci in Dockerfile frontend-builder stage
|
||||
([`b4e0067`](https://github.com/christianlouis/DocuElevate/commit/b4e0067a27e2fb161349bd38c6d3b3f3bcb86972))
|
||||
|
||||
### Documentation
|
||||
|
||||
- **changelog**: Update changelog [skip ci]
|
||||
([`0841713`](https://github.com/christianlouis/DocuElevate/commit/084171395d1076c716aa500a516118db49468ff5))
|
||||
|
||||
|
||||
## Unreleased
|
||||
|
||||
|
||||
## v0.172.1 (2026-03-22)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- Social login providers now work from DB config without restart
|
||||
([`0c7ea67`](https://github.com/christianlouis/DocuElevate/commit/0c7ea6748da554c80ef9af1b709c08aba49174e6))
|
||||
|
||||
|
||||
## v0.172.0 (2026-03-22)
|
||||
|
||||
### Features
|
||||
|
||||
- **ui**: Migrate Tailwind CSS from v2 CDN to v3 Play CDN (interim step)
|
||||
([`1d7df13`](https://github.com/christianlouis/DocuElevate/commit/1d7df13c943cc9138dc3ed514f9ab81d861bfbac))
|
||||
|
||||
- **ui**: Replace Tailwind CSS CDN with compiled v3 production build
|
||||
([`14b3031`](https://github.com/christianlouis/DocuElevate/commit/14b3031e63e8645c4048dd73a594e9a53a919c17))
|
||||
|
||||
|
||||
## v0.171.3 (2026-03-22)
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
+19
-2
@@ -27,7 +27,21 @@ RUN pip install --no-cache-dir -r requirements.txt \
|
||||
&& find /opt/venv -type f -name "*.pyc" -delete \
|
||||
&& find /opt/venv -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null || true
|
||||
|
||||
# ── Stage 2: Documentation builder ──────────────────────────────────────────
|
||||
# ── Stage 2: Frontend asset builder ─────────────────────────────────────────
|
||||
# Compiles Tailwind CSS (a devDependency) into the minified styles.css.
|
||||
# npm ci installs ALL deps (including devDependencies) so the tailwindcss CLI
|
||||
# is available; using --omit=dev would cause 'tailwindcss: not found'.
|
||||
FROM node:20-slim AS frontend-builder
|
||||
|
||||
WORKDIR /frontend
|
||||
|
||||
COPY frontend/package.json frontend/package-lock.json ./
|
||||
RUN npm ci
|
||||
|
||||
COPY frontend/ ./
|
||||
RUN npm run build
|
||||
|
||||
# ── Stage 4: Documentation builder ──────────────────────────────────────────
|
||||
FROM python:3.14.3-slim AS docs-builder
|
||||
|
||||
WORKDIR /docs
|
||||
@@ -43,7 +57,7 @@ COPY mkdocs.yml /docs/mkdocs.yml
|
||||
# Build the static documentation site
|
||||
RUN mkdocs build --config-file /docs/mkdocs.yml --site-dir /docs/docs_build
|
||||
|
||||
# ── Stage 3: Runtime image ───────────────────────────────────────────────────
|
||||
# ── Stage 5: Runtime image ───────────────────────────────────────────────────
|
||||
FROM python:3.14.3-slim
|
||||
|
||||
WORKDIR /app
|
||||
@@ -81,6 +95,9 @@ COPY ./RUNTIME_INFO /app/RUNTIME_INFO
|
||||
# Copy the pre-built MkDocs documentation site (served at /help)
|
||||
COPY --from=docs-builder /docs/docs_build /app/docs_build
|
||||
|
||||
# Copy the compiled Tailwind CSS (built in the frontend-builder stage)
|
||||
COPY --from=frontend-builder /frontend/static/styles.css /app/frontend/static/styles.css
|
||||
|
||||
# Create necessary runtime directories in a single layer
|
||||
RUN mkdir -p /app/runtime_info /workdir
|
||||
|
||||
|
||||
+115
-69
@@ -1,6 +1,6 @@
|
||||
# DocuElevate Milestones
|
||||
|
||||
**Last Updated:** 2026-02-08
|
||||
**Last Updated:** 2026-05-23
|
||||
|
||||
This document outlines the release milestones, versioning strategy, and detailed feature breakdown for DocuElevate.
|
||||
|
||||
@@ -19,17 +19,15 @@ DocuElevate follows [Semantic Versioning 2.0.0](https://semver.org/):
|
||||
|
||||
---
|
||||
|
||||
## Current Release: v0.5.0 (February 2026)
|
||||
## Current State (Continuous Releases)
|
||||
|
||||
### Status: Stable
|
||||
- Production-ready document processing
|
||||
- Multi-provider storage support
|
||||
- **Database-backed settings management with encryption**
|
||||
- **Setup wizard for first-time configuration**
|
||||
- **Admin UI for runtime configuration**
|
||||
- **Automated semantic versioning and releases**
|
||||
- OAuth2 authentication with admin group support
|
||||
- Basic web UI and REST API
|
||||
DocuElevate ships continuously via automated semantic versioning. Use **GitHub Releases** for the latest build artifacts and **GitHub Milestones** (below) for roadmap tracking.
|
||||
|
||||
### Last Shipped Milestone: v0.5.0 (Released February 8, 2026)
|
||||
- Database-backed settings management with encryption
|
||||
- Setup wizard for first-time configuration
|
||||
- Admin UI for runtime configuration
|
||||
- Release automation via semantic-release
|
||||
|
||||
### Important Note on Versioning
|
||||
As of February 2026, DocuElevate uses **automated semantic versioning**:
|
||||
@@ -130,87 +128,78 @@ As of February 2026, DocuElevate uses **automated semantic versioning**:
|
||||
|
||||
## Upcoming Milestones
|
||||
|
||||
### v0.6.0 - Enhanced Search & UI Improvements (April 2026)
|
||||
**Target Date:** April 1, 2026
|
||||
### v0.6.0 - Clarity: Enhanced Search & UI (Target: July 31, 2026)
|
||||
**Target Date:** July 31, 2026
|
||||
**Status:** 📋 Planned
|
||||
**Theme:** User Experience, Search, Performance
|
||||
**Theme:** Search, Discovery, Modern UX
|
||||
**Epic:** #863
|
||||
|
||||
#### Goals
|
||||
- Implement full-text search across documents
|
||||
- Responsive mobile interface
|
||||
- Dark mode support
|
||||
- Document preview in browser
|
||||
- Performance optimizations
|
||||
- Improved error handling and user feedback
|
||||
- Hybrid discovery: keyword + semantic search, fast filtering, saved searches
|
||||
- Preview-first UX (open, skim, and act quickly)
|
||||
- Modern UX polish (accessibility, responsiveness, performance)
|
||||
|
||||
#### Deliverables
|
||||
- Full-text search API and UI
|
||||
- Advanced filtering capabilities
|
||||
- Responsive CSS framework integration
|
||||
- Dark mode toggle
|
||||
- In-browser document viewer
|
||||
- Loading states and progress indicators
|
||||
- Performance benchmarks
|
||||
- Mobile-optimized interface
|
||||
- Semantic search foundation (vectorization + ranking signals)
|
||||
- Saved searches / smart views
|
||||
- In-browser preview + “quick actions” (tag, route, export)
|
||||
- Bulk operations and pagination improvements
|
||||
- UX polish (dark mode/accessibility where applicable)
|
||||
|
||||
#### Breaking Changes
|
||||
- API response format changes for search endpoints (documented)
|
||||
- Potential pagination/search response changes (must be versioned and documented)
|
||||
|
||||
#### Migration Path
|
||||
- Search endpoint changes will be versioned (/api/v1/search → /api/v2/search)
|
||||
- Old endpoints deprecated but functional for 2 releases
|
||||
- Version endpoints where needed and keep previous versions working for at least 2 minor milestones
|
||||
|
||||
---
|
||||
|
||||
### v0.4.5 - Workflow Automation (June 2026)
|
||||
**Target Date:** June 1, 2026
|
||||
### v0.7.0 - Conductor: Workflow Automation & Integrations (Target: September 30, 2026)
|
||||
**Target Date:** September 30, 2026
|
||||
**Status:** 📋 Planned
|
||||
**Theme:** Automation, Integration, Webhooks
|
||||
**Epic:** #864
|
||||
|
||||
#### Goals
|
||||
- Custom processing pipelines
|
||||
- Conditional routing based on document type
|
||||
- Webhook support for external integrations
|
||||
- Rule-based classification
|
||||
- Scheduled batch processing
|
||||
- First-class workflow model (steps, state, retries) that matches what the system actually executes
|
||||
- Workflow-aware UI status, retries, and observability
|
||||
- Webhooks + event-driven automation foundations
|
||||
|
||||
#### Deliverables
|
||||
- Pipeline configuration UI
|
||||
- Webhook management interface
|
||||
- Rule engine for document routing
|
||||
- Batch processing scheduler
|
||||
- Integration examples and templates
|
||||
- Webhook payload documentation
|
||||
- Workflow object model and storage
|
||||
- Workflow-aware file detail view + status dashboard
|
||||
- Scheduling primitives (recurring jobs / delayed runs)
|
||||
- Webhook system (outbound events + inbound triggers)
|
||||
- Integration templates and documentation
|
||||
|
||||
---
|
||||
|
||||
### v0.7.0 - Advanced AI & Multi-language (August 2026)
|
||||
**Target Date:** August 1, 2026
|
||||
### v0.8.0 - Signal: AI Quality, RAG, and Multi-language (Target: November 30, 2026)
|
||||
**Target Date:** November 30, 2026
|
||||
**Status:** 📋 Planned
|
||||
**Theme:** AI Enhancement, Internationalization
|
||||
**Theme:** AI Quality, Retrieval, Internationalization
|
||||
**Epic:** #865
|
||||
|
||||
#### Goals
|
||||
- Custom AI model support
|
||||
- Multi-language OCR
|
||||
- Document similarity detection
|
||||
- Duplicate detection
|
||||
- UI internationalization (i18n)
|
||||
- API localization
|
||||
- “Chat with Library” foundations (retrieval + UI)
|
||||
- Local AI options for privacy-sensitive setups
|
||||
- Measurable AI quality (confidence + human review loop)
|
||||
- Expand multilingual capability across OCR + UI
|
||||
|
||||
#### Deliverables
|
||||
- Custom model integration API
|
||||
- Multi-language OCR configuration
|
||||
- Similarity algorithm implementation
|
||||
- Duplicate detection service
|
||||
- Translation framework (10+ languages)
|
||||
- Localized documentation
|
||||
- Vector DB integration and embeddings pipeline
|
||||
- Chat UI foundations and retrieval API
|
||||
- Confidence scoring + human review/edit loop for extracted fields
|
||||
- Multi-language OCR configuration improvements
|
||||
- Expanded i18n coverage + localized docs
|
||||
|
||||
---
|
||||
|
||||
### v1.0.0 - Enterprise Edition (November 2026)
|
||||
**Target Date:** November 1, 2026
|
||||
### v1.0.0 - Summit: Enterprise Edition (Target: March 31, 2027)
|
||||
**Target Date:** March 31, 2027
|
||||
**Status:** 📋 Planned
|
||||
**Theme:** Enterprise Features, Scalability, Multi-tenancy
|
||||
**Epic:** #866
|
||||
|
||||
This is our first major release, marking production-ready enterprise capabilities.
|
||||
|
||||
@@ -244,6 +233,60 @@ This is our first major release, marking production-ready enterprise capabilitie
|
||||
|
||||
---
|
||||
|
||||
### v2.0.0 - Horizon: Platform Expansion (Target: September 30, 2027)
|
||||
**Target Date:** September 30, 2027
|
||||
**Status:** 📋 Planned
|
||||
**Theme:** Ecosystem, Platform, Distribution
|
||||
**Epic:** #867
|
||||
|
||||
#### Goals
|
||||
- Make DocuElevate extensible by design (plugins + templates)
|
||||
- Expand integrations and developer experience
|
||||
- Harden multi-surface experiences (web, mobile, extension, CLI) as a cohesive product
|
||||
|
||||
#### Deliverables
|
||||
- Plugin system foundations and public extension points
|
||||
- Template library for pipelines/workflows + “starter kits”
|
||||
- Integration hub patterns (webhooks, events, connectors)
|
||||
- SDK + documentation for extensions
|
||||
|
||||
---
|
||||
|
||||
### v2.1.0 - Sentinel: Governance & Policy (Target: March 31, 2028)
|
||||
**Target Date:** March 31, 2028
|
||||
**Status:** 📋 Planned
|
||||
**Theme:** Governance, Compliance, Policy-driven Automation
|
||||
**Epic:** #868
|
||||
|
||||
#### Goals
|
||||
- Make governance first-class (retention, legal hold, PII workflows)
|
||||
- Provide tamper-evident auditing and admin controls
|
||||
- Introduce policy-driven approvals for sensitive automation
|
||||
|
||||
#### Deliverables
|
||||
- Retention policies + legal hold primitives
|
||||
- PII detection + redaction workflows
|
||||
- Tamper-evident audit trails + admin activity feed
|
||||
- Policy-as-code concepts for workflows (with approval gates)
|
||||
|
||||
---
|
||||
|
||||
### v3.0.0 - Constellation: Integration Hub & Agent Platform (Target: September 30, 2028)
|
||||
**Target Date:** September 30, 2028
|
||||
**Status:** 📋 Planned
|
||||
**Theme:** Ecosystem, Agents, Interoperability
|
||||
**Epic:** #869
|
||||
|
||||
#### Goals
|
||||
- Make DocuElevate the “system of record” for document intelligence in an organization
|
||||
- Support external automation ecosystems (Zapier/Make/n8n) and agent runtimes
|
||||
- Provide a clean interoperability layer for modern AI tools
|
||||
|
||||
#### Deliverables
|
||||
- DocuElevate MCP server (search, retrieve, summarize, route) and documentation
|
||||
- Connector marketplace concepts (curated + community)
|
||||
- Event stream + webhooks at scale (delivery guarantees, retries, signing)
|
||||
|
||||
## Release Process
|
||||
|
||||
### Automated Semantic Versioning (v0.6.0+)
|
||||
@@ -255,15 +298,15 @@ Starting with v0.6.0, releases are fully automated using `python-semantic-releas
|
||||
4. **Automatic Updates**:
|
||||
- Updates `VERSION` file
|
||||
- Generates/updates `CHANGELOG.md`
|
||||
- Creates Git tag (e.g., `v0.6.0`)
|
||||
- Creates Git tag (e.g., `v0.173.1`)
|
||||
- Creates GitHub Release with notes
|
||||
- Triggers Docker image builds
|
||||
5. **No Manual Steps**: VERSION and CHANGELOG are never edited manually
|
||||
|
||||
### Version Bump Rules
|
||||
- `feat:` commits → Minor version (0.5.0 → 0.6.0)
|
||||
- `fix:`, `perf:` → Patch version (0.5.0 → 0.5.1)
|
||||
- `feat!:`, `BREAKING CHANGE:` → Major version (0.5.0 → 1.0.0)
|
||||
- `feat:` commits → Minor version (e.g., 0.173.1 → 0.174.0)
|
||||
- `fix:`, `perf:` → Patch version (e.g., 0.173.1 → 0.173.2)
|
||||
- `feat!:`, `BREAKING CHANGE:` → Major version (e.g., 0.173.1 → 1.0.0)
|
||||
- Other types (docs, chore, etc.) → No version bump
|
||||
|
||||
### Pre-release Checklist (Automated)
|
||||
@@ -297,10 +340,13 @@ Starting with v0.6.0, releases are fully automated using `python-semantic-releas
|
||||
| v0.3.2 | 2026-02-06 | Security Updates | Released |
|
||||
| v0.3.3 | 2026-02-08 | Drag-and-Drop Upload | Released |
|
||||
| v0.5.0 | 2026-02-08 | **Settings & Encryption** | **Released** |
|
||||
| v0.6.0 | 2026-04 | Search & UX | Planned |
|
||||
| v0.7.0 | 2026-08 | Advanced AI | Planned |
|
||||
| v1.0.0 | 2026-11 | Enterprise | Planned |
|
||||
| v2.0.0 | 2027-Q3 | Platform Expansion | Future |
|
||||
| v0.6.0 | 2026-07-31 | **Clarity:** Search & UX | Planned |
|
||||
| v0.7.0 | 2026-09-30 | **Conductor:** Workflows & Integrations | Planned |
|
||||
| v0.8.0 | 2026-11-30 | **Signal:** AI Quality, RAG, Multi-language | Planned |
|
||||
| v1.0.0 | 2027-03-31 | **Summit:** Enterprise | Planned |
|
||||
| v2.0.0 | 2027-09-30 | **Horizon:** Platform Expansion | Future |
|
||||
| v2.1.0 | 2028-03-31 | **Sentinel:** Governance & Policy | Future |
|
||||
| v3.0.0 | 2028-09-30 | **Constellation:** Integration Hub & Agents | Future |
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -35,7 +35,7 @@ DocuElevate is an intelligent document processing system that automates the inge
|
||||
|
||||
- **AI-Powered Metadata Extraction** — pluggable AI providers including OpenAI, Anthropic Claude, Google Gemini, Ollama (local), OpenRouter, Portkey, and Azure OpenAI via LiteLLM
|
||||
- **Multi-Engine OCR** — Azure Document Intelligence, Tesseract, EasyOCR, Mistral OCR, Google Cloud Document AI, and AWS Textract with configurable merge strategies
|
||||
- **12 Storage Destinations** — Dropbox, Google Drive, OneDrive, Amazon S3, Nextcloud, WebDAV, FTP, SFTP, iCloud Drive, Email (SMTP), Paperless-ngx, and Rclone
|
||||
- **13 Storage Destinations** — Dropbox, Google Drive, OneDrive, Amazon S3, Nextcloud, WebDAV, FTP, SFTP, iCloud Drive, Email (SMTP), Paperless-ngx, Evernote, and Rclone
|
||||
- **Multi-Channel Ingestion** — web upload, browser extension, mobile app, CLI, REST API, IMAP email, and watched folders (local, cloud, FTP/SFTP)
|
||||
- **Processing Pipelines** — customizable multi-step workflows with conditional routing rules
|
||||
- **Full-Text Search** — powered by Meilisearch for instant document discovery
|
||||
@@ -106,6 +106,7 @@ Processed documents are distributed to any combination of configured destination
|
||||
| **iCloud Drive** | Apple cloud |
|
||||
| **Email (SMTP)** | Send as attachment |
|
||||
| **Paperless-ngx** | Document management system |
|
||||
| **Evernote** | Notes with PDF attachments |
|
||||
| **Rclone** | 70+ cloud providers via Rclone |
|
||||
|
||||
## Features
|
||||
@@ -245,6 +246,7 @@ See the [Kubernetes Deployment Guide](docs/KubernetesDeployment.md) for full det
|
||||
| [Google Drive](docs/GoogleDriveSetup.md) | Google Drive service account / OAuth |
|
||||
| [OneDrive](docs/OneDriveSetup.md) | Microsoft OneDrive setup |
|
||||
| [Amazon S3](docs/AmazonS3Setup.md) | S3 bucket configuration |
|
||||
| [Evernote](docs/EvernoteSetup.md) | Evernote note creation |
|
||||
| [Authentication](docs/AuthenticationSetup.md) | OAuth2, OIDC, and social login |
|
||||
| [Notifications](docs/NotificationsSetup.md) | Notification backend setup |
|
||||
|
||||
@@ -327,6 +329,7 @@ The following is a summary of the licenses used by our direct dependencies:
|
||||
| pypdf | BSD |
|
||||
| Requests | Apache 2.0 |
|
||||
| Dropbox SDK | MIT |
|
||||
| Evernote SDK | BSD |
|
||||
| Azure AI Document Intelligence | MIT |
|
||||
| Authlib | BSD |
|
||||
| Starlette | BSD |
|
||||
|
||||
+103
-133
@@ -1,169 +1,139 @@
|
||||
# DocuElevate Roadmap
|
||||
|
||||
**Last Updated:** 2026-02-08
|
||||
**Version:** 1.0
|
||||
**Last Updated:** 2026-05-23
|
||||
**Version:** 2.0
|
||||
|
||||
## Vision
|
||||
|
||||
DocuElevate aims to be the premier open-source intelligent document processing platform, providing seamless integration with cloud storage providers, advanced AI-powered metadata extraction, and enterprise-grade security and scalability.
|
||||
|
||||
## How to Read This Roadmap
|
||||
|
||||
DocuElevate ships frequently (automated semantic versioning), so this roadmap is organized around **milestone outcomes** and **themes**, not exact build numbers.
|
||||
|
||||
- **P0** = required for the milestone to feel “done”
|
||||
- **P1** = strongly desired; may slip if needed
|
||||
- **P2** = nice-to-have / opportunistic
|
||||
|
||||
For the detailed milestone breakdown and target dates, see [MILESTONES.md](MILESTONES.md).
|
||||
|
||||
## Release Naming
|
||||
|
||||
Each major milestone release carries a codename to anchor key project moments. These names appear in the status dashboard, build metadata, and changelog. For details, see [docs/ReleaseNaming.md](docs/ReleaseNaming.md).
|
||||
|
||||
| Version Range | Codename | Theme |
|
||||
|---------------|---------------|--------------------------------------------------|
|
||||
| 0.5.x | **Foundation** | Core platform, multi-provider storage, AI, UI |
|
||||
| 0.6.x | **Clarity** | Enhanced search, filtering, UI/UX improvements |
|
||||
| 0.7.x | **Conductor** | Workflow automation, pipelines, rule-based logic |
|
||||
| 1.0.x | **Summit** | Enterprise features, multi-tenancy, RBAC |
|
||||
| 1.1.x | **Bridge** | Collaboration, sharing, analytics |
|
||||
| 2.0.x | **Horizon** | On-premise AI, platform expansion |
|
||||
| Milestone | Codename | Theme |
|
||||
|----------|------------------|-------|
|
||||
| v0.6.0 | **Clarity** | Search, discovery, and modern UX |
|
||||
| v0.7.0 | **Conductor** | Workflows, orchestration, and integrations |
|
||||
| v0.8.0 | **Signal** | AI quality, multilingual, and “Chat with Library” foundations |
|
||||
| v1.0.0 | **Summit** | Enterprise readiness (multi-tenancy, RBAC, scaling) |
|
||||
| v2.0.0 | **Horizon** | Platform expansion and ecosystem maturity |
|
||||
| v2.1.0+ | **Sentinel** | Governance, compliance, and policy-driven automation |
|
||||
| v3.0.0 | **Constellation**| Integration hub, agents, and interoperability |
|
||||
|
||||
## Current Status (v0.5.0 "Foundation")
|
||||
## Current Product Capabilities (Today)
|
||||
|
||||
### Core Features ✅
|
||||
- Multi-provider document storage (Dropbox, Google Drive, OneDrive, Nextcloud, S3, etc.)
|
||||
- IMAP email integration for document ingestion
|
||||
- OCR processing via Azure Document Intelligence
|
||||
- AI-powered metadata extraction via OpenAI
|
||||
- PDF conversion via Gotenberg
|
||||
- Web UI for document upload and management
|
||||
- **Database-backed settings management with admin UI**
|
||||
- **Fernet encryption for sensitive configuration**
|
||||
- **Setup wizard for first-time installation**
|
||||
- REST API with OpenAPI documentation
|
||||
- Celery-based async task processing
|
||||
- OAuth2 authentication via Authentik with admin group support
|
||||
- Multi-channel ingestion (web upload, IMAP email, watched folders, mobile, CLI, API)
|
||||
- Multi-engine OCR + AI extraction with configurable providers
|
||||
- Customizable processing pipelines and routing rules
|
||||
- Full-text search and document discovery
|
||||
- Multi-destination distribution (cloud providers, DMS, protocols, email)
|
||||
- Admin UI for configuration (database-backed settings, encryption, setup wizard)
|
||||
- Production hardening building blocks (CI/CD, security docs, deployment guides)
|
||||
|
||||
## Short-term Goals (Q1-Q2 2026) - v0.4.x to v0.5.x "Foundation"
|
||||
## Feature Landscape (Themes)
|
||||
|
||||
### Quality & Stability 🎯
|
||||
- **Test Coverage** (High Priority)
|
||||
- [ ] Achieve 80% code coverage for core modules
|
||||
- [ ] Add integration tests for all storage providers
|
||||
- [ ] Add end-to-end workflow tests
|
||||
- [ ] Performance benchmarks and load testing
|
||||
### 1) Search & Discovery
|
||||
- **P0:** hybrid search (keyword + semantic), fast faceted filtering, saved searches
|
||||
- **P1:** “explain results” (why a document matched), query suggestions, pinned results
|
||||
- **P2:** entity search (people/companies/amounts/dates) and graph-style exploration
|
||||
|
||||
- **Code Quality** (High Priority)
|
||||
- [ ] Enable strict linting in CI/CD
|
||||
- [ ] Refactor large modules for better maintainability
|
||||
- [ ] Add comprehensive type hints
|
||||
- [ ] Improve error handling and user feedback
|
||||
### 2) AI Quality & Trust
|
||||
- **P0:** confidence scoring, human review/edit loop, extraction evaluation harness
|
||||
- **P1:** per-document-type schemas/templates, active learning (feedback improves extraction)
|
||||
- **P2:** multi-model routing (choose model by cost/latency/accuracy per step)
|
||||
|
||||
- **Security** (Critical Priority)
|
||||
- [x] Fix known vulnerabilities in dependencies
|
||||
- [ ] Implement rate limiting on API endpoints
|
||||
- [ ] Add CSRF protection
|
||||
- [ ] Security audit by external party
|
||||
- [ ] Implement API key rotation
|
||||
- [ ] Add audit logging for sensitive operations
|
||||
### 3) Workflow Automation & Orchestration
|
||||
- **P0:** first-class workflow model (steps, state, retries), workflow-aware UI status
|
||||
- **P1:** visual workflow builder, scheduling, webhooks, and event-driven triggers
|
||||
- **P2:** agentic workflows (“autopilot” suggestions with approval gates)
|
||||
|
||||
- **Release Automation** (Completed ✅)
|
||||
- [x] Implement semantic-release for automated versioning
|
||||
- [x] Add conventional commit validation
|
||||
- [x] Automate CHANGELOG generation
|
||||
- [x] Integrate Docker builds with releases
|
||||
### 4) Integrations & Ecosystem (Including MCP)
|
||||
- **P0:** stable webhooks + outbound actions (Slack/Teams, email, DMS), bi-directional sync where supported
|
||||
- **P1:** “Integration Hub” (Zapier/Make/n8n style), connector templates, secrets handling patterns
|
||||
- **P2:** **MCP**: ship a DocuElevate MCP server (search, retrieve, summarize, route) + allow MCP tools as pipeline steps
|
||||
|
||||
### Features - v0.4.0
|
||||
- **Enhanced Search & Filtering** → _preparing for v0.6.0 "Clarity"_
|
||||
- [ ] Full-text search across documents
|
||||
- [ ] Advanced filtering by metadata, tags, date ranges
|
||||
- [ ] Saved search queries
|
||||
- [ ] Bulk operations on search results
|
||||
### 5) Governance, Compliance, and Security
|
||||
- **P0:** audit trails, tamper-evident logs, API key lifecycle/rotation, admin activity feed
|
||||
- **P1:** retention policies, legal hold, PII detection + redaction, data residency controls
|
||||
- **P2:** compliance packs (SOC2/GDPR/HIPAA), BYOK/KMS integration paths
|
||||
|
||||
- **Improved UI/UX**
|
||||
- [ ] Responsive mobile interface
|
||||
- [ ] Dark mode support
|
||||
- [ ] Document preview in browser
|
||||
- [ ] Drag-and-drop file upload
|
||||
- [ ] Progress indicators for long-running tasks
|
||||
- [ ] Real-time notifications via WebSocket
|
||||
### 6) Enterprise & Scale
|
||||
- **P0:** multi-tenancy, RBAC, horizontal scaling reference architecture
|
||||
- **P1:** SCIM provisioning, SAML/Okta/Azure AD hardening, quotas/billing at org level
|
||||
- **P2:** multi-region deployment patterns and disaster recovery playbooks
|
||||
|
||||
### Features - v0.5.0 "Foundation"
|
||||
- **Workflow Automation** → _evolving into v0.7.0 "Conductor"_
|
||||
- [ ] Custom processing pipelines
|
||||
- [ ] Conditional routing based on document type
|
||||
- [ ] Scheduled batch processing
|
||||
- [ ] Webhook support for external integrations
|
||||
- [ ] Rule-based document classification
|
||||
## Release Plan (Extended)
|
||||
|
||||
- **Advanced AI Features**
|
||||
- [ ] Custom AI models for specialized document types
|
||||
- [ ] Multi-language OCR support
|
||||
- [ ] Document similarity detection
|
||||
- [ ] Automatic duplicate detection
|
||||
- [ ] Intelligent document splitting
|
||||
This plan extends the existing milestones with a clearer thematic arc and a forward-looking “beyond v2.0” horizon. Each milestone links to an epic issue that owns scope and sub-issues.
|
||||
|
||||
## Medium-term Goals (Q3-Q4 2026) - v1.0.x "Summit"
|
||||
### v0.6.0 — Clarity (Search & UX)
|
||||
- **Outcome:** users can reliably find, preview, and act on documents in seconds
|
||||
- **P0:** semantic search + hybrid ranking, saved searches, fast filters, preview-first UX
|
||||
- **P1:** bulk operations, query suggestions, accessibility/dark mode polish
|
||||
- **Tracking:** GitHub milestone `v0.6.0 - Enhanced Search & UI` (epic #863)
|
||||
|
||||
### Enterprise Features - v1.0.0 "Summit"
|
||||
- **Multi-tenancy**
|
||||
- [ ] Organization/team management
|
||||
- [ ] Role-based access control (RBAC)
|
||||
- [ ] Per-tenant configuration
|
||||
- [ ] Resource quotas and limits
|
||||
- [ ] Audit logs per organization
|
||||
### v0.7.0 — Conductor (Workflows & Integrations)
|
||||
- **Outcome:** workflows are explicit, inspectable, and automatable end-to-end
|
||||
- **P0:** workflow object model + workflow-aware UI status, retries, pipeline definitions
|
||||
- **P1:** workflow builder, scheduling, inbound/outbound webhooks
|
||||
- **P2:** integration templates + “connector marketplace” concepts
|
||||
- **Tracking:** GitHub milestone `v0.7.0 - Workflow Automation` (epic #864)
|
||||
|
||||
- **Scalability**
|
||||
- [ ] Horizontal scaling support
|
||||
- [ ] Distributed task processing
|
||||
- [ ] Caching layer (Redis/Memcached)
|
||||
- [ ] Database connection pooling
|
||||
- [ ] Message queue optimization
|
||||
### v0.8.0 — Signal (AI Quality + “Chat with Library” Foundations)
|
||||
- **Outcome:** AI features are measurable, reviewable, and safe to trust
|
||||
- **P0:** vector DB + embeddings pipeline, chat UI foundations, local AI options
|
||||
- **P1:** confidence scoring and review loop, extraction evaluation harness
|
||||
- **P2:** multilingual UX + localization expansion
|
||||
- **Tracking:** GitHub milestone `v0.8.0 - Advanced AI & Multi-language` (epic #865)
|
||||
|
||||
- **Advanced Integrations**
|
||||
- [ ] Microsoft SharePoint integration
|
||||
- [ ] Slack/Teams bot integration
|
||||
- [ ] Zapier/Make.com integration
|
||||
- [ ] Custom webhook receivers
|
||||
- [ ] GraphQL API
|
||||
### v1.0.0 — Summit (Enterprise Readiness)
|
||||
- **Outcome:** teams can run DocuElevate with strong isolation, access control, and scale
|
||||
- **P0:** multi-tenancy, RBAC, audit logging, scaling guidance
|
||||
- **P1:** SSO hardening (SAML/LDAP), org-level quotas and billing hooks
|
||||
- **P2:** enterprise admin experience (policies, approvals, reporting)
|
||||
- **Tracking:** GitHub milestone `v1.0.0 - Enterprise Edition` (epic #866)
|
||||
|
||||
### Features - v1.1.0 "Bridge"
|
||||
- **Collaboration**
|
||||
- [ ] Document sharing with expiring links
|
||||
- [ ] Comments and annotations
|
||||
- [ ] Version history and rollback
|
||||
- [ ] Real-time collaborative editing metadata
|
||||
- [ ] Activity feed
|
||||
### v2.0.0 — Horizon (Platform Expansion)
|
||||
- **Outcome:** DocuElevate becomes an extensible platform with a thriving ecosystem
|
||||
- **P0:** plugin system foundations, SDK + templates, deeper integrations
|
||||
- **P1:** marketplace patterns, app distribution, mobile/extension maturity
|
||||
- **P2:** multi-workspace experiences (personal + org)
|
||||
- **Tracking:** GitHub milestone `v2.0.0 - Platform Expansion` (epic #867)
|
||||
|
||||
- **Reporting & Analytics**
|
||||
- [ ] Processing statistics dashboard
|
||||
- [ ] Storage usage analytics
|
||||
- [ ] AI confidence scores and accuracy tracking
|
||||
- [ ] Cost analysis per provider
|
||||
- [ ] Export reports (PDF, CSV, Excel)
|
||||
### v2.1.0+ — Sentinel (Governance & Policy)
|
||||
- **Outcome:** governance becomes a first-class layer (policy-driven automation)
|
||||
- **P0:** retention + legal hold, PII detection/redaction, tamper-evident audit trails
|
||||
- **P1:** BYOK/KMS integration patterns, advanced access policies, compliance reporting
|
||||
- **P2:** “policy as code” for workflows + approvals (change management)
|
||||
- **Tracking:** GitHub milestone `v2.1.0 - Governance & Policy (Sentinel)` (epic #868)
|
||||
|
||||
## Long-term Goals (2027+) - v2.0+ "Horizon"
|
||||
### v3.0.0 — Constellation (Integration Hub & Agent Platform)
|
||||
- **Outcome:** DocuElevate plugs into modern automation and AI ecosystems as a first-class system of record
|
||||
- **P0:** MCP server, durable event stream + production-grade webhooks
|
||||
- **P1:** connector templates + curated catalog, agent-friendly permissioning and auditing
|
||||
- **P2:** bring-your-own-agent patterns (sandboxing, scoped credentials)
|
||||
- **Tracking:** GitHub milestone `v3.0.0 - Integration Hub & Agent Platform (Constellation)` (epic #869)
|
||||
|
||||
### Strategic Initiatives
|
||||
- **On-Premise AI Models**
|
||||
- [ ] Self-hosted OCR (Tesseract, EasyOCR)
|
||||
- [ ] Local LLM integration (Ollama, LLaMA)
|
||||
- [ ] GPU acceleration support
|
||||
- [ ] Model fine-tuning interface
|
||||
- [ ] Hybrid cloud/on-premise processing
|
||||
## Research Bets (Optional / Experimental)
|
||||
|
||||
- **Advanced Document Management**
|
||||
- [ ] Document lifecycle management
|
||||
- [ ] Retention policies and auto-deletion
|
||||
- [ ] Compliance templates (GDPR, HIPAA, SOC2)
|
||||
- [ ] Digital signature support
|
||||
- [ ] Encryption at rest and in transit
|
||||
These are longer-horizon bets that should only be productized if they prove real user value.
|
||||
|
||||
- **Platform Expansion**
|
||||
- [ ] Desktop applications (Electron)
|
||||
- [ ] Mobile apps (iOS/Android)
|
||||
- [ ] Browser extensions
|
||||
- [ ] Command-line interface (CLI)
|
||||
- [ ] VS Code extension for developers
|
||||
|
||||
### Research & Innovation
|
||||
- [ ] Machine learning for custom document types
|
||||
- [ ] Blockchain for document provenance
|
||||
- [ ] Federated learning for privacy-preserving AI
|
||||
- [ ] Edge computing support
|
||||
- [ ] Quantum-resistant encryption
|
||||
- Knowledge graph over extracted entities (contracts ↔ vendors ↔ invoices)
|
||||
- Auto-generated “case files” (collections) from intent (“tax 2025”, “project alpha”)
|
||||
- Privacy-preserving learning (federated patterns) to improve extraction quality
|
||||
- Document provenance (signing, attestations) and tamper detection
|
||||
|
||||
## Community & Ecosystem
|
||||
|
||||
|
||||
+6
-6
@@ -1,10 +1,10 @@
|
||||
DocuElevate Build Information
|
||||
==============================
|
||||
Version: 0.171.3
|
||||
Build Date: 2026-03-22T17:46:27Z
|
||||
Git Commit: 720c9c11b05a7af6ac33478ecab6cc80c24c83e1
|
||||
Git Short SHA: 720c9c1
|
||||
Version: 0.173.4
|
||||
Build Date: 2026-06-01T03:41:15Z
|
||||
Git Commit: 425805ab23882944aee0cb02b5e497bc536549c0
|
||||
Git Short SHA: 425805a
|
||||
Git Branch: main
|
||||
Commit Date: 2026-03-22T18:46:06+01:00
|
||||
Build Timestamp: 2026-03-22T17:46:27Z
|
||||
Commit Date: 2026-06-01T05:40:53+02:00
|
||||
Build Timestamp: 2026-06-01T03:41:16Z
|
||||
==============================
|
||||
|
||||
+1
-1
@@ -260,7 +260,7 @@ async def stripe_webhook(request: Request, db: Session = Depends(get_db)) -> dic
|
||||
@require_login
|
||||
async def billing_success(request: Request) -> Any:
|
||||
"""Show a success page after a completed Stripe Checkout."""
|
||||
return _templates.TemplateResponse("billing_success.html", {"request": request})
|
||||
return _templates.TemplateResponse(request, "billing_success.html")
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
+13
-2
@@ -25,6 +25,17 @@ logger = logging.getLogger(__name__)
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
def _require_admin(request: Request) -> dict:
|
||||
"""Ensure the caller is an admin. Raises 403 otherwise."""
|
||||
user = request.session.get("user")
|
||||
if not user or not user.get("is_admin"):
|
||||
raise HTTPException(status_code=status.HTTP_403_FORBIDDEN, detail="Admin access required")
|
||||
return user
|
||||
|
||||
|
||||
AdminUser = Annotated[dict, Depends(_require_admin)]
|
||||
|
||||
|
||||
def _build_dropbox_redirect_uri(request: Request) -> str:
|
||||
"""Build the Dropbox OAuth callback redirect URI.
|
||||
|
||||
@@ -385,14 +396,14 @@ async def list_dropbox_folders(
|
||||
|
||||
|
||||
@router.post("/dropbox/save-settings")
|
||||
@require_login
|
||||
async def save_dropbox_settings(
|
||||
request: Request,
|
||||
refresh_token: Annotated[str, Form(...)],
|
||||
_admin: AdminUser,
|
||||
db: Session = Depends(get_db),
|
||||
app_key: Annotated[Optional[str], Form()] = None,
|
||||
app_secret: Annotated[Optional[str], Form()] = None,
|
||||
folder_path: Annotated[Optional[str], Form()] = None,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
Save Dropbox settings to database (primary) and .env file (best-effort).
|
||||
|
||||
+25
-12
@@ -23,6 +23,17 @@ logger = logging.getLogger(__name__)
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
def _require_admin(request: Request) -> dict:
|
||||
"""Ensure the caller is an admin. Raises 403 otherwise."""
|
||||
user = request.session.get("user")
|
||||
if not user or not user.get("is_admin"):
|
||||
raise HTTPException(status_code=status.HTTP_403_FORBIDDEN, detail="Admin access required")
|
||||
return user
|
||||
|
||||
|
||||
AdminUser = Annotated[dict, Depends(_require_admin)]
|
||||
|
||||
|
||||
@router.post("/google-drive/exchange-token")
|
||||
@require_login
|
||||
async def exchange_google_drive_token(
|
||||
@@ -362,15 +373,15 @@ def format_time_remaining(time_delta):
|
||||
|
||||
|
||||
@router.post("/google-drive/save-settings")
|
||||
@require_login
|
||||
async def save_google_drive_settings(
|
||||
request: Request,
|
||||
refresh_token: Annotated[str, Form(...)],
|
||||
_admin: AdminUser,
|
||||
db: Session = Depends(get_db),
|
||||
client_id: Annotated[Optional[str], Form()] = None,
|
||||
client_secret: Annotated[Optional[str], Form()] = None,
|
||||
folder_id: Annotated[Optional[str], Form()] = None,
|
||||
use_oauth: Annotated[str, Form()] = "true",
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
Save Google Drive settings to the .env file (best-effort) and persist to database.
|
||||
@@ -403,9 +414,10 @@ async def save_google_drive_settings(
|
||||
if folder_id:
|
||||
drive_settings["GOOGLE_DRIVE_FOLDER_ID"] = folder_id
|
||||
|
||||
# Try to update the .env file, but don't fail if it doesn't exist (for Docker containers)
|
||||
if os.path.exists(env_path):
|
||||
try:
|
||||
# Best-effort .env file write — failures here are non-fatal
|
||||
env_file_written = False
|
||||
try:
|
||||
if os.path.exists(env_path):
|
||||
logger.info(f"Updating Google Drive settings in {env_path}")
|
||||
|
||||
# Read the current .env file
|
||||
@@ -438,12 +450,13 @@ async def save_google_drive_settings(
|
||||
f.write("\n".join(new_env_lines) + "\n")
|
||||
|
||||
logger.info("Successfully updated Google Drive settings in .env file")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to update .env file: {str(e)}, but will continue with in-memory update")
|
||||
else:
|
||||
logger.warning(
|
||||
f".env file not found at {env_path}, skipping file update but continuing with in-memory update"
|
||||
)
|
||||
env_file_written = True
|
||||
else:
|
||||
logger.warning(
|
||||
f".env file not found at {env_path}, skipping file update but continuing with in-memory update"
|
||||
)
|
||||
except Exception as env_err:
|
||||
logger.warning(f"Failed to write .env file (non-fatal): {env_err}")
|
||||
|
||||
# Update the settings in memory (this always happens)
|
||||
if refresh_token:
|
||||
@@ -481,7 +494,7 @@ async def save_google_drive_settings(
|
||||
return {
|
||||
"status": "success",
|
||||
"message": "Google Drive settings have been saved",
|
||||
"in_memory_only": not os.path.exists(env_path),
|
||||
"in_memory_only": not env_file_written,
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
|
||||
@@ -17,6 +17,7 @@ from sqlalchemy.orm import Session
|
||||
from app.database import get_db
|
||||
from app.models import UserImapAccount
|
||||
from app.utils.encryption import decrypt_value, encrypt_value
|
||||
from app.utils.network import is_private_ip
|
||||
from app.utils.subscription import get_tier, get_user_tier_id
|
||||
from app.utils.user_scope import get_current_owner_id
|
||||
|
||||
@@ -187,6 +188,11 @@ def _test_imap_connection(host: str, port: int, username: str, password: str, us
|
||||
|
||||
Returns a dict with ``{"success": bool, "message": str}``.
|
||||
"""
|
||||
|
||||
# Security: Prevent SSRF by blocking connections to internal IPs
|
||||
if is_private_ip(host):
|
||||
logger.warning("SSRF blocked: Attempt to connect to private IP %s", host)
|
||||
return {"success": False, "message": "Connection error: Invalid hostname or IP address"}
|
||||
try:
|
||||
if use_ssl:
|
||||
mail = imaplib.IMAP4_SSL(host, port)
|
||||
|
||||
+18
-1
@@ -515,6 +515,12 @@ def _test_imap_connection(config: dict[str, Any] | None, credentials: dict[str,
|
||||
if not host or not username or not password:
|
||||
return {"success": False, "message": "Missing required fields: host, username, and password"}
|
||||
|
||||
from app.utils.network import is_private_ip
|
||||
|
||||
if is_private_ip(host):
|
||||
logger.warning("SSRF blocked: Attempt to connect to private IP %s", host)
|
||||
return {"success": False, "message": "Connection error: Invalid hostname or IP address"}
|
||||
|
||||
try:
|
||||
if use_ssl:
|
||||
mail = imaplib.IMAP4_SSL(host, port)
|
||||
@@ -543,17 +549,28 @@ def _test_s3_connection(config: dict[str, Any] | None, credentials: dict[str, An
|
||||
creds = credentials or {}
|
||||
bucket = cfg.get("bucket", "")
|
||||
region = cfg.get("region", "us-east-1")
|
||||
endpoint_url = cfg.get("endpoint_url")
|
||||
|
||||
if not bucket:
|
||||
return {"success": False, "message": "Missing required field: bucket"}
|
||||
|
||||
if endpoint_url:
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from app.utils.network import is_private_ip
|
||||
|
||||
parsed_url = urlparse(endpoint_url)
|
||||
if parsed_url.hostname and is_private_ip(parsed_url.hostname):
|
||||
logger.warning("SSRF blocked: Attempt to connect to private IP via S3 endpoint %s", endpoint_url)
|
||||
return {"success": False, "message": "Connection error: Invalid endpoint URL or private IP"}
|
||||
|
||||
try:
|
||||
client = boto3.client(
|
||||
"s3",
|
||||
region_name=region,
|
||||
aws_access_key_id=creds.get("access_key_id", ""),
|
||||
aws_secret_access_key=creds.get("secret_access_key", ""),
|
||||
endpoint_url=cfg.get("endpoint_url"),
|
||||
endpoint_url=endpoint_url,
|
||||
)
|
||||
client.head_bucket(Bucket=bucket)
|
||||
return {"success": True, "message": f"S3 bucket '{bucket}' is accessible"}
|
||||
|
||||
@@ -101,9 +101,9 @@ async def signup_page(request: Request) -> Any:
|
||||
if not settings.allow_local_signup:
|
||||
return RedirectResponse(url="/login?error=Registration+is+not+enabled", status_code=302)
|
||||
return templates.TemplateResponse(
|
||||
request,
|
||||
"signup.html",
|
||||
{
|
||||
"request": request,
|
||||
context={
|
||||
"csrf_token": getattr(request.state, "csrf_token", ""),
|
||||
"app_version": settings.version,
|
||||
},
|
||||
@@ -113,16 +113,16 @@ async def signup_page(request: Request) -> Any:
|
||||
@router.get("/verify-email-sent", include_in_schema=False)
|
||||
async def verify_email_sent_page(request: Request) -> Any:
|
||||
"""Render the verify-email-sent confirmation page."""
|
||||
return templates.TemplateResponse("verify_email_sent.html", {"request": request})
|
||||
return templates.TemplateResponse(request, "verify_email_sent.html")
|
||||
|
||||
|
||||
@router.get("/forgot-username", include_in_schema=False)
|
||||
async def forgot_username_page(request: Request) -> Any:
|
||||
"""Render the forgot-username page where users can request a username reminder email."""
|
||||
return templates.TemplateResponse(
|
||||
request,
|
||||
"forgot_username.html",
|
||||
{
|
||||
"request": request,
|
||||
context={
|
||||
"csrf_token": getattr(request.state, "csrf_token", ""),
|
||||
"app_version": settings.version,
|
||||
},
|
||||
@@ -133,9 +133,9 @@ async def forgot_username_page(request: Request) -> Any:
|
||||
async def forgot_password_page(request: Request) -> Any:
|
||||
"""Render the forgot-password page where users can request a reset email."""
|
||||
return templates.TemplateResponse(
|
||||
request,
|
||||
"forgot_password.html",
|
||||
{
|
||||
"request": request,
|
||||
context={
|
||||
"csrf_token": getattr(request.state, "csrf_token", ""),
|
||||
"app_version": settings.version,
|
||||
},
|
||||
@@ -147,9 +147,9 @@ async def reset_password_page(request: Request) -> Any:
|
||||
"""Render the password reset form page."""
|
||||
token = request.query_params.get("token", "")
|
||||
return templates.TemplateResponse(
|
||||
request,
|
||||
"password_reset_form.html",
|
||||
{
|
||||
"request": request,
|
||||
context={
|
||||
"token": token,
|
||||
"csrf_token": getattr(request.state, "csrf_token", ""),
|
||||
"app_version": settings.version,
|
||||
|
||||
+13
-2
@@ -25,6 +25,17 @@ logger = logging.getLogger(__name__)
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
def _require_admin(request: Request) -> dict:
|
||||
"""Ensure the caller is an admin. Raises 403 otherwise."""
|
||||
user = request.session.get("user")
|
||||
if not user or not user.get("is_admin"):
|
||||
raise HTTPException(status_code=status.HTTP_403_FORBIDDEN, detail="Admin access required")
|
||||
return user
|
||||
|
||||
|
||||
AdminUser = Annotated[dict, Depends(_require_admin)]
|
||||
|
||||
|
||||
@router.post("/onedrive/exchange-token")
|
||||
@require_login
|
||||
async def exchange_onedrive_token(
|
||||
@@ -302,15 +313,15 @@ def format_time_remaining(time_delta):
|
||||
|
||||
|
||||
@router.post("/onedrive/save-settings")
|
||||
@require_login
|
||||
async def save_onedrive_settings(
|
||||
request: Request,
|
||||
refresh_token: Annotated[str, Form(...)],
|
||||
_admin: AdminUser,
|
||||
db: Session = Depends(get_db),
|
||||
client_id: Annotated[Optional[str], Form()] = None,
|
||||
client_secret: Annotated[Optional[str], Form()] = None,
|
||||
tenant_id: Annotated[str, Form()] = "common",
|
||||
folder_path: Annotated[Optional[str], Form()] = None,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
Saves to database (primary) and .env file (best-effort).
|
||||
|
||||
@@ -9,7 +9,7 @@ Public endpoints:
|
||||
"""
|
||||
|
||||
import logging
|
||||
from datetime import datetime, timezone
|
||||
from datetime import datetime, time, timedelta, timezone
|
||||
from typing import Annotated, Any
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, Request, status
|
||||
@@ -207,19 +207,29 @@ def platform_stats(request: Request, db: DbSession, _admin: AdminUser) -> dict[s
|
||||
from app.models import FileRecord, UserProfile
|
||||
|
||||
today = datetime.now(timezone.utc).date()
|
||||
day_start = datetime.combine(today, time.min, tzinfo=timezone.utc)
|
||||
day_end = day_start + timedelta(days=1)
|
||||
month_start = day_start.replace(day=1)
|
||||
if month_start.month == 12:
|
||||
month_end = month_start.replace(year=month_start.year + 1, month=1)
|
||||
else:
|
||||
month_end = month_start.replace(month=month_start.month + 1)
|
||||
|
||||
# Total files
|
||||
total_files: int = db.query(func.count(FileRecord.id)).scalar() or 0
|
||||
|
||||
# Files today
|
||||
files_today: int = (
|
||||
db.query(func.count(FileRecord.id)).filter(func.date(FileRecord.created_at) == today).scalar() or 0
|
||||
db.query(func.count(FileRecord.id))
|
||||
.filter(FileRecord.created_at >= day_start, FileRecord.created_at < day_end)
|
||||
.scalar()
|
||||
or 0
|
||||
)
|
||||
|
||||
# Files this month
|
||||
files_this_month: int = (
|
||||
db.query(func.count(FileRecord.id))
|
||||
.filter(func.strftime("%Y-%m", FileRecord.created_at) == today.strftime("%Y-%m"))
|
||||
.filter(FileRecord.created_at >= month_start, FileRecord.created_at < month_end)
|
||||
.scalar()
|
||||
or 0
|
||||
)
|
||||
|
||||
@@ -28,6 +28,10 @@ logger = logging.getLogger(__name__)
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
class UnsafeRedirectError(httpx.RequestError):
|
||||
"""Raised when a redirect target fails URL safety checks."""
|
||||
|
||||
|
||||
class URLUploadRequest(BaseModel):
|
||||
"""Request model for URL-based file upload"""
|
||||
|
||||
@@ -106,6 +110,26 @@ def validate_file_type(content_type: str, filename: str) -> bool:
|
||||
return False
|
||||
|
||||
|
||||
async def verify_redirect(response: httpx.Response) -> None:
|
||||
"""
|
||||
Event hook to intercept redirects and validate the new destination URL.
|
||||
Prevents SSRF bypasses via redirects to internal networks or metadata endpoints.
|
||||
"""
|
||||
if response.status_code in (301, 302, 303, 307, 308):
|
||||
location = response.headers.get("Location")
|
||||
if location:
|
||||
# Resolve relative redirects
|
||||
new_url = str(response.url.join(location))
|
||||
# Validate the new URL
|
||||
try:
|
||||
validate_url_safety(new_url)
|
||||
except HTTPException as e:
|
||||
raise UnsafeRedirectError(
|
||||
f"Redirect to unsafe URL blocked: {e.detail}",
|
||||
request=response.request,
|
||||
) from e
|
||||
|
||||
|
||||
@router.post("/process-url")
|
||||
@require_login
|
||||
async def process_url(
|
||||
@@ -162,6 +186,7 @@ async def process_url(
|
||||
async with httpx.AsyncClient(
|
||||
timeout=settings.http_request_timeout,
|
||||
follow_redirects=True,
|
||||
event_hooks={"response": [verify_redirect]},
|
||||
headers={
|
||||
"User-Agent": "DocuElevate/1.0", # Identify ourselves
|
||||
},
|
||||
@@ -251,6 +276,10 @@ async def process_url(
|
||||
logger.error(f"HTTP error while downloading file from URL: {url} - {str(e)}")
|
||||
raise HTTPException(status_code=e.response.status_code, detail=f"HTTP error: {str(e)}")
|
||||
|
||||
except UnsafeRedirectError as e:
|
||||
logger.warning(f"Unsafe redirect blocked while downloading file from URL: {url} - {str(e)}")
|
||||
raise HTTPException(status_code=400, detail=str(e))
|
||||
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"Error downloading file from URL: {url} - {str(e)}")
|
||||
raise HTTPException(status_code=500, detail=f"Failed to download file: {str(e)}")
|
||||
|
||||
+3
-3
@@ -280,7 +280,7 @@ def _setup_social_providers() -> None:
|
||||
"icon": "fas fa-sign-in-alt",
|
||||
"color": "indigo",
|
||||
}
|
||||
logger.info("Social login provider registered: Generic OAuth2 (%s)", _generic_name)
|
||||
logger.info("Social login provider registered: Generic OAuth2")
|
||||
else:
|
||||
logger.warning("SOCIAL_AUTH_GENERIC_OAUTH2_ENABLED=true but required settings not configured")
|
||||
|
||||
@@ -536,9 +536,9 @@ async def login(request: Request):
|
||||
return RedirectResponse(url="/oauth-login", status_code=status.HTTP_302_FOUND)
|
||||
|
||||
return templates.TemplateResponse(
|
||||
request,
|
||||
"login.html",
|
||||
{
|
||||
"request": request,
|
||||
context={
|
||||
"error": error,
|
||||
"message": message,
|
||||
"show_oauth": show_oauth,
|
||||
|
||||
@@ -46,6 +46,7 @@ from app.tasks.translate_to_default_language import translate_to_default_languag
|
||||
# Import new send tasks
|
||||
from app.tasks.upload_to_dropbox import upload_to_dropbox # noqa: F401
|
||||
from app.tasks.upload_to_email import upload_to_email # noqa: F401
|
||||
from app.tasks.upload_to_evernote import upload_to_evernote # noqa: F401
|
||||
from app.tasks.upload_to_ftp import upload_to_ftp # noqa: F401
|
||||
from app.tasks.upload_to_google_drive import upload_to_google_drive # noqa: F401
|
||||
from app.tasks.upload_to_icloud import upload_to_icloud # noqa: F401
|
||||
|
||||
@@ -154,6 +154,17 @@ class Settings(BaseSettings):
|
||||
# "language": "Language", "correspondent": "Correspondent"}
|
||||
paperless_custom_fields_mapping: Optional[str] = None
|
||||
|
||||
# Evernote destination settings
|
||||
evernote_enabled: bool = Field(
|
||||
default=True,
|
||||
description="Enable Evernote as an upload destination. Set to False to disable uploads even when credentials are configured.",
|
||||
)
|
||||
evernote_auth_token: Optional[str] = None
|
||||
evernote_sandbox: bool = False
|
||||
evernote_notebook_guid: Optional[str] = None
|
||||
evernote_default_tags: Optional[str] = None
|
||||
evernote_include_metadata: bool = True
|
||||
|
||||
azure_ai_key: str
|
||||
azure_region: str
|
||||
azure_endpoint: str
|
||||
|
||||
+12
-7
@@ -294,10 +294,16 @@ async def lifespan(app: FastAPI):
|
||||
yield
|
||||
|
||||
# Shutdown: Cleanup tasks
|
||||
logging.info("Application shutting down")
|
||||
try:
|
||||
logging.info("Application shutting down")
|
||||
except Exception:
|
||||
_startup_logger.exception("Error during shutdown logging")
|
||||
|
||||
# Send shutdown notification
|
||||
notify_shutdown()
|
||||
try:
|
||||
notify_shutdown()
|
||||
except Exception:
|
||||
_startup_logger.exception("Error sending shutdown notification")
|
||||
|
||||
|
||||
app = FastAPI(
|
||||
@@ -424,15 +430,13 @@ async def http_exception_handler(request: Request, exc: HTTPException):
|
||||
# For frontend routes, return appropriate HTML templates
|
||||
# Handle 404 errors with a custom template
|
||||
if exc.status_code == 404:
|
||||
return _error_templates.TemplateResponse(
|
||||
"404.html", {"request": request}, status_code=status.HTTP_404_NOT_FOUND
|
||||
)
|
||||
return _error_templates.TemplateResponse(request, "404.html", status_code=status.HTTP_404_NOT_FOUND)
|
||||
|
||||
# For other HTTP errors, we could create specific templates or use a generic one
|
||||
# For now, return a simple error page
|
||||
return _error_templates.TemplateResponse(
|
||||
request,
|
||||
"404.html", # Reuse 404 template for other errors, or create a generic error template
|
||||
{"request": request},
|
||||
status_code=exc.status_code,
|
||||
)
|
||||
|
||||
@@ -452,8 +456,9 @@ async def custom_500_handler(request: Request, exc: Exception):
|
||||
|
||||
# Serve the 500 template for non-API routes
|
||||
return _error_templates.TemplateResponse(
|
||||
request,
|
||||
"500.html",
|
||||
{"request": request, "exc": exc},
|
||||
context={"exc": exc},
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
)
|
||||
|
||||
|
||||
@@ -205,7 +205,7 @@ def convert_to_pdf(
|
||||
".pdf", # PDF (already in PDF format but can be processed)
|
||||
}
|
||||
|
||||
IMAGE_EXTENSIONS = {".jpg", ".jpeg", ".png", ".gif", ".bmp", ".tiff", ".tif", ".webp", ".svg", ".heic", ".heif"}
|
||||
IMAGE_EXTENSIONS = {".jpg", ".jpeg", ".png", ".gif", ".bmp", ".tiff", ".tif", ".webp", ".svg"}
|
||||
|
||||
HTML_EXTENSIONS = {".html", ".htm"}
|
||||
|
||||
|
||||
@@ -78,7 +78,7 @@ def _convert_pdf_to_pdfa(input_path: str, output_path: str, pdfa_format: str = "
|
||||
output_type,
|
||||
"--quiet",
|
||||
"--invalidate-digital-signatures",
|
||||
"--",
|
||||
"--", # end-of-options separator: prevents file paths from being interpreted as options
|
||||
input_path,
|
||||
output_path,
|
||||
]
|
||||
|
||||
@@ -76,7 +76,7 @@ def extract_metadata_with_gpt(self, filename: str, cleaned_text: str, file_id: i
|
||||
"Your task is to analyze the given text and return a well-structured JSON object.\n\n"
|
||||
"Extract and return the following fields:\n"
|
||||
"1. **filename**: Machine-readable filename "
|
||||
"(YYYY-MM-DD_DescriptiveTitle, use only letters, numbers, spaces, dashes, periods, and underscores).\n"
|
||||
"(YYYY-MM-DD_DescriptiveTitle, use only letters, numbers, periods, and underscores).\n"
|
||||
'2. **empfaenger**: The recipient, or "Unknown" if not found.\n'
|
||||
'3. **absender**: The sender, or "Unknown" if not found.\n'
|
||||
"4. **correspondent**: The entity or company that issued the document "
|
||||
|
||||
@@ -18,6 +18,7 @@ from app.utils.allowed_types import (
|
||||
DEFAULT_CATEGORIES,
|
||||
get_allowed_types_for_categories,
|
||||
)
|
||||
from app.utils.network import is_private_ip
|
||||
|
||||
# Database session for per-user IMAP accounts (imported lazily to avoid circular imports)
|
||||
_db_session_factory = None
|
||||
@@ -405,6 +406,11 @@ def pull_inbox(
|
||||
)
|
||||
processed_emails = load_processed_emails()
|
||||
|
||||
# Security: Prevent SSRF by blocking connections to internal IPs
|
||||
if is_private_ip(host):
|
||||
logger.warning("SSRF blocked: Attempt to pull mailbox from private IP %s", host)
|
||||
return
|
||||
|
||||
try:
|
||||
mail = imaplib.IMAP4_SSL(host, port) if use_ssl else imaplib.IMAP4(host, port)
|
||||
mail.login(username, password)
|
||||
|
||||
@@ -10,6 +10,7 @@ from app.models import FileRecord, IntegrationDirection, UserIntegration
|
||||
from app.tasks.retry_config import BaseTaskWithRetry
|
||||
from app.tasks.upload_to_dropbox import upload_to_dropbox
|
||||
from app.tasks.upload_to_email import upload_to_email
|
||||
from app.tasks.upload_to_evernote import upload_to_evernote
|
||||
from app.tasks.upload_to_ftp import upload_to_ftp
|
||||
from app.tasks.upload_to_google_drive import upload_to_google_drive
|
||||
from app.tasks.upload_to_icloud import upload_to_icloud
|
||||
@@ -100,6 +101,11 @@ def _should_upload_to_email():
|
||||
)
|
||||
|
||||
|
||||
def _should_upload_to_evernote():
|
||||
token = getattr(settings, "evernote_auth_token", None)
|
||||
return bool(getattr(settings, "evernote_enabled", True) and isinstance(token, str) and token.strip())
|
||||
|
||||
|
||||
def _should_upload_to_onedrive():
|
||||
return bool(
|
||||
getattr(settings, "onedrive_enabled", True)
|
||||
@@ -151,6 +157,7 @@ def get_configured_services_from_validator():
|
||||
"FTP Storage": "ftp",
|
||||
"SFTP Storage": "sftp",
|
||||
"Email": "email",
|
||||
"Evernote": "evernote",
|
||||
"OneDrive": "onedrive",
|
||||
"S3 Storage": "s3",
|
||||
"SharePoint": "sharepoint",
|
||||
@@ -254,6 +261,11 @@ def send_to_all_destinations(self, file_path: str, use_validator=True, file_id:
|
||||
"should_upload": _should_upload_to_email,
|
||||
"upload_func": upload_to_email,
|
||||
},
|
||||
{
|
||||
"name": "evernote",
|
||||
"should_upload": _should_upload_to_evernote,
|
||||
"upload_func": upload_to_evernote,
|
||||
},
|
||||
{
|
||||
"name": "onedrive",
|
||||
"should_upload": _should_upload_to_onedrive,
|
||||
|
||||
@@ -0,0 +1,242 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import logging
|
||||
import mimetypes
|
||||
import os
|
||||
from html import escape
|
||||
from typing import Any
|
||||
|
||||
from app.celery_app import celery
|
||||
from app.config import settings
|
||||
from app.tasks.retry_config import UploadTaskWithRetry
|
||||
from app.utils import log_task_progress
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_UNKNOWN_PLACEHOLDERS = {"", "Unknown", "unknown", "N/A", "n/a", "None", "none", "null"}
|
||||
_MAX_EVERNOTE_TITLE_LENGTH = 255
|
||||
|
||||
|
||||
def _get_evernote_sdk():
|
||||
"""Import the Evernote SDK lazily so the missing dependency error is actionable."""
|
||||
try:
|
||||
from evernote.edam.notestore import NoteStore
|
||||
from evernote.edam.type import ttypes as Types
|
||||
from evernote.edam.userstore import UserStore
|
||||
from thrift.protocol import TBinaryProtocol
|
||||
from thrift.transport import THttpClient
|
||||
except ImportError as exc:
|
||||
raise RuntimeError("Evernote upload requires the evernote3 package. Install requirements.txt again.") from exc
|
||||
return NoteStore, Types, UserStore, TBinaryProtocol, THttpClient
|
||||
|
||||
|
||||
def _build_thrift_client(client_cls, url: str, binary_protocol, http_transport):
|
||||
transport = http_transport.THttpClient(url)
|
||||
protocol = binary_protocol.TBinaryProtocol(transport)
|
||||
return client_cls(protocol)
|
||||
|
||||
|
||||
def _get_note_store(auth_token: str):
|
||||
NoteStore, Types, UserStore, TBinaryProtocol, THttpClient = _get_evernote_sdk()
|
||||
|
||||
base_url = (
|
||||
"https://sandbox.evernote.com" if getattr(settings, "evernote_sandbox", False) else "https://www.evernote.com"
|
||||
)
|
||||
user_store = _build_thrift_client(UserStore.Client, f"{base_url}/edam/user", TBinaryProtocol, THttpClient)
|
||||
user = user_store.getUser(auth_token)
|
||||
shard_id = getattr(user, "shardId", None)
|
||||
if not shard_id:
|
||||
raise RuntimeError("Evernote user response did not include a shard ID")
|
||||
|
||||
note_store_url = f"{base_url}/shard/{shard_id}/notestore"
|
||||
note_store = _build_thrift_client(NoteStore.Client, note_store_url, TBinaryProtocol, THttpClient)
|
||||
return note_store, Types
|
||||
|
||||
|
||||
def _load_metadata(file_path: str) -> dict[str, Any]:
|
||||
"""Load extracted DocuElevate metadata from the companion JSON file, when present."""
|
||||
json_path = os.path.splitext(file_path)[0] + ".json"
|
||||
if not os.path.exists(json_path):
|
||||
return {}
|
||||
|
||||
try:
|
||||
with open(json_path, "r", encoding="utf-8") as metadata_file:
|
||||
data = json.load(metadata_file)
|
||||
except Exception as exc: # noqa: BLE001
|
||||
logger.warning("Failed to load Evernote metadata from %s: %s", json_path, exc)
|
||||
return {}
|
||||
|
||||
return data if isinstance(data, dict) else {}
|
||||
|
||||
|
||||
def _normalize_metadata_value(value: Any) -> str:
|
||||
if value is None:
|
||||
return ""
|
||||
if isinstance(value, (list, tuple, set)):
|
||||
normalized = ", ".join(str(item) for item in value if item is not None)
|
||||
elif isinstance(value, dict):
|
||||
normalized = json.dumps(value, ensure_ascii=False, sort_keys=True)
|
||||
else:
|
||||
normalized = str(value)
|
||||
|
||||
normalized = normalized.strip()
|
||||
return "" if normalized in _UNKNOWN_PLACEHOLDERS else normalized
|
||||
|
||||
|
||||
def _metadata_rows(metadata: dict[str, Any]) -> list[tuple[str, str]]:
|
||||
rows = []
|
||||
for key in sorted(metadata):
|
||||
value = _normalize_metadata_value(metadata[key])
|
||||
if value:
|
||||
rows.append((key, value))
|
||||
return rows
|
||||
|
||||
|
||||
def _extract_tags(metadata: dict[str, Any]) -> list[str]:
|
||||
tags: list[str] = []
|
||||
|
||||
def add_tag(value: Any) -> None:
|
||||
normalized = _normalize_metadata_value(value)
|
||||
if normalized and normalized not in tags:
|
||||
tags.append(normalized)
|
||||
|
||||
default_tags = getattr(settings, "evernote_default_tags", None)
|
||||
if default_tags:
|
||||
for tag in str(default_tags).split(","):
|
||||
add_tag(tag)
|
||||
|
||||
metadata_tags = metadata.get("tags")
|
||||
if isinstance(metadata_tags, str):
|
||||
for tag in metadata_tags.split(","):
|
||||
add_tag(tag)
|
||||
elif isinstance(metadata_tags, (list, tuple, set)):
|
||||
for tag in metadata_tags:
|
||||
add_tag(tag)
|
||||
|
||||
return tags
|
||||
|
||||
|
||||
def _note_title(file_path: str, metadata: dict[str, Any]) -> str:
|
||||
title = (
|
||||
_normalize_metadata_value(metadata.get("title"))
|
||||
or _normalize_metadata_value(metadata.get("filename"))
|
||||
or os.path.basename(file_path)
|
||||
)
|
||||
return title[:_MAX_EVERNOTE_TITLE_LENGTH]
|
||||
|
||||
|
||||
def _build_enml(metadata: dict[str, Any], resource_hash: str, resource_mime: str, include_metadata: bool) -> str:
|
||||
body_parts = ['<?xml version="1.0" encoding="UTF-8"?>']
|
||||
body_parts.append('<!DOCTYPE en-note SYSTEM "http://xml.evernote.com/pub/enml2.dtd">')
|
||||
body_parts.append("<en-note>")
|
||||
|
||||
if include_metadata:
|
||||
rows = _metadata_rows(metadata)
|
||||
if rows:
|
||||
body_parts.append("<div><b>DocuElevate metadata</b></div>")
|
||||
for key, value in rows:
|
||||
body_parts.append(f"<div><b>{escape(key)}:</b> {escape(value)}</div>")
|
||||
body_parts.append("<br/>")
|
||||
|
||||
body_parts.append(f'<en-media type="{escape(resource_mime)}" hash="{resource_hash}"/>')
|
||||
body_parts.append("</en-note>")
|
||||
return "".join(body_parts)
|
||||
|
||||
|
||||
def _create_evernote_note(file_path: str, metadata: dict[str, Any], task_id: str):
|
||||
auth_token = getattr(settings, "evernote_auth_token", None)
|
||||
if not auth_token:
|
||||
raise ValueError("Evernote auth token is not configured (EVERNOTE_AUTH_TOKEN)")
|
||||
|
||||
note_store, Types = _get_note_store(auth_token)
|
||||
|
||||
filename = os.path.basename(file_path)
|
||||
with open(file_path, "rb") as pdf_file:
|
||||
resource_body = pdf_file.read()
|
||||
|
||||
body_hash = hashlib.md5(resource_body).digest() # noqa: S324 - Evernote API requires MD5 resource hashes.
|
||||
body_hash_hex = hashlib.md5(resource_body).hexdigest() # noqa: S324 - Evernote ENML references MD5 hashes.
|
||||
resource_mime = mimetypes.guess_type(filename)[0] or "application/pdf"
|
||||
|
||||
data = Types.Data()
|
||||
data.size = len(resource_body)
|
||||
data.bodyHash = body_hash
|
||||
data.body = resource_body
|
||||
|
||||
resource = Types.Resource()
|
||||
resource.mime = resource_mime
|
||||
resource.data = data
|
||||
resource.attributes = Types.ResourceAttributes(fileName=filename)
|
||||
|
||||
note = Types.Note()
|
||||
note.title = _note_title(file_path, metadata)
|
||||
note.content = _build_enml(
|
||||
metadata,
|
||||
body_hash_hex,
|
||||
resource_mime,
|
||||
include_metadata=getattr(settings, "evernote_include_metadata", True),
|
||||
)
|
||||
note.resources = [resource]
|
||||
|
||||
notebook_guid = getattr(settings, "evernote_notebook_guid", None)
|
||||
if notebook_guid:
|
||||
note.notebookGuid = notebook_guid
|
||||
|
||||
tag_names = _extract_tags(metadata)
|
||||
if tag_names:
|
||||
note.tagNames = tag_names
|
||||
|
||||
created_note = note_store.createNote(auth_token, note)
|
||||
|
||||
logger.info("[%s] Created Evernote note %s for %s", task_id, getattr(created_note, "guid", None), file_path)
|
||||
return created_note
|
||||
|
||||
|
||||
@celery.task(base=UploadTaskWithRetry, bind=True)
|
||||
def upload_to_evernote(self, file_path: str, file_id: int = None):
|
||||
"""
|
||||
Upload a document to Evernote by creating a note with metadata and a PDF attachment.
|
||||
|
||||
Args:
|
||||
file_path: Path to the PDF file to upload
|
||||
file_id: Optional file ID to associate with logs
|
||||
"""
|
||||
task_id = self.request.id
|
||||
filename = os.path.basename(file_path)
|
||||
logger.info("[%s] Starting Evernote upload: %s", task_id, file_path)
|
||||
log_task_progress(
|
||||
task_id, "upload_to_evernote", "in_progress", f"Uploading to Evernote: {filename}", file_id=file_id
|
||||
)
|
||||
|
||||
if not os.path.exists(file_path):
|
||||
error_msg = f"File not found: {file_path}"
|
||||
logger.error("[%s] %s", task_id, error_msg)
|
||||
log_task_progress(task_id, "upload_to_evernote", "failure", error_msg, file_id=file_id)
|
||||
raise FileNotFoundError(error_msg)
|
||||
|
||||
if not getattr(settings, "evernote_auth_token", None):
|
||||
error_msg = "Evernote auth token is not configured (EVERNOTE_AUTH_TOKEN)"
|
||||
logger.error("[%s] %s", task_id, error_msg)
|
||||
log_task_progress(task_id, "upload_to_evernote", "failure", error_msg, file_id=file_id)
|
||||
raise ValueError(error_msg)
|
||||
|
||||
try:
|
||||
metadata = _load_metadata(file_path)
|
||||
created_note = _create_evernote_note(file_path, metadata, task_id)
|
||||
except Exception as exc:
|
||||
error_msg = f"Failed to upload to Evernote: {exc}"
|
||||
logger.error("[%s] %s", task_id, error_msg)
|
||||
log_task_progress(task_id, "upload_to_evernote", "failure", error_msg, file_id=file_id)
|
||||
raise
|
||||
|
||||
note_guid = getattr(created_note, "guid", None)
|
||||
log_task_progress(task_id, "upload_to_evernote", "success", f"Uploaded to Evernote: {note_guid}", file_id=file_id)
|
||||
return {
|
||||
"status": "Completed",
|
||||
"file_path": file_path,
|
||||
"evernote_note_guid": note_guid,
|
||||
"evernote_title": getattr(created_note, "title", None),
|
||||
"evernote_notebook_guid": getattr(created_note, "notebookGuid", None),
|
||||
}
|
||||
@@ -555,9 +555,8 @@ def _upload_rclone(file_path: str, cfg: dict[str, Any], creds: dict[str, Any], t
|
||||
dest = dest.replace("//", "/")
|
||||
|
||||
try:
|
||||
# SECURITY: Separate options from positional arguments using -- to prevent command injection
|
||||
result = subprocess.run( # nosec B603 # noqa: S603 S607
|
||||
["rclone", "copyto", f"--config={conf_path}", "--", file_path, dest], # noqa: S603 S607
|
||||
["rclone", "copyto", f"--config={conf_path}", file_path, dest], # noqa: S603 S607
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=300,
|
||||
|
||||
@@ -174,6 +174,21 @@ def get_provider_status() -> dict[str, dict[str, object]]:
|
||||
},
|
||||
}
|
||||
|
||||
providers["Evernote"] = {
|
||||
"name": "Evernote",
|
||||
"icon": "fa-brands fa-evernote",
|
||||
"configured": bool(getattr(settings, "evernote_auth_token", None)),
|
||||
"enabled": getattr(settings, "evernote_enabled", True),
|
||||
"description": "Create Evernote notes with document metadata and PDF attachments",
|
||||
"details": {
|
||||
"auth_token": mask_sensitive_value(getattr(settings, "evernote_auth_token", None)),
|
||||
"sandbox": getattr(settings, "evernote_sandbox", False),
|
||||
"notebook_guid": getattr(settings, "evernote_notebook_guid", "Not set"),
|
||||
"default_tags": getattr(settings, "evernote_default_tags", "Not set"),
|
||||
"include_metadata": getattr(settings, "evernote_include_metadata", True),
|
||||
},
|
||||
}
|
||||
|
||||
# Add FTP configuration to providers
|
||||
providers["FTP Storage"] = {
|
||||
"name": "FTP Storage",
|
||||
|
||||
@@ -145,6 +145,12 @@ def validate_storage_configs() -> dict[str, list[str]]:
|
||||
email_issues.append("DEST_EMAIL_DEFAULT_RECIPIENT is not configured")
|
||||
issues["email"] = email_issues
|
||||
|
||||
# Validate Evernote
|
||||
evernote_issues = []
|
||||
if not getattr(settings, "evernote_auth_token", None):
|
||||
evernote_issues.append("EVERNOTE_AUTH_TOKEN is not configured")
|
||||
issues["evernote"] = evernote_issues
|
||||
|
||||
# Validate S3
|
||||
s3_issues = []
|
||||
if not getattr(settings, "s3_bucket_name", None):
|
||||
|
||||
@@ -15,7 +15,7 @@ import logging
|
||||
import re
|
||||
from typing import Any
|
||||
|
||||
from sqlalchemy import MetaData, create_engine, inspect, text
|
||||
from sqlalchemy import MetaData, create_engine, func, inspect, select, table
|
||||
from sqlalchemy.engine import Engine
|
||||
from sqlalchemy.engine.url import make_url
|
||||
from sqlalchemy.orm import sessionmaker
|
||||
@@ -89,8 +89,9 @@ def preview_migration(source_url: str) -> dict[str, Any]:
|
||||
logger.warning(f"Skipping table with invalid name format: {table_name}")
|
||||
continue
|
||||
# table_name is safe — sourced from inspect().get_table_names(), not user input
|
||||
quoted_table = conn.dialect.identifier_preparer.quote(table_name)
|
||||
row = conn.execute(text(f"SELECT COUNT(*) FROM {quoted_table}")).fetchone() # noqa: S608
|
||||
t = table(table_name)
|
||||
query = select(func.count()).select_from(t)
|
||||
row = conn.execute(query).fetchone()
|
||||
count = row[0] if row else 0
|
||||
result.append({"name": table_name, "row_count": count})
|
||||
total += count
|
||||
|
||||
@@ -1,11 +1,10 @@
|
||||
import logging
|
||||
import os
|
||||
from typing import Dict
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def update_env_file(settings_to_update: Dict[str, str]) -> bool:
|
||||
def update_env_file(settings_to_update: dict[str, str]) -> bool:
|
||||
"""
|
||||
Updates the .env file with the given settings (best-effort).
|
||||
Creates or modifies existing keys.
|
||||
|
||||
@@ -7,8 +7,19 @@ def hash_file(filepath: str | Path, chunk_size: int = 65536) -> str:
|
||||
Returns the SHA-256 hash of the file at 'filepath'.
|
||||
Reads the file in chunks to handle large files efficiently.
|
||||
"""
|
||||
from app.config import settings
|
||||
|
||||
filepath_obj = Path(filepath).resolve()
|
||||
workdir_obj = Path(settings.workdir).resolve()
|
||||
|
||||
# Security check: Ensure the resolved path is strictly within the allowed workdir
|
||||
try:
|
||||
filepath_obj.relative_to(workdir_obj)
|
||||
except ValueError:
|
||||
raise FileNotFoundError(f"Access denied: path traversal attempt or file outside workdir '{filepath}'")
|
||||
|
||||
sha256 = hashlib.sha256()
|
||||
with open(filepath, "rb") as f:
|
||||
with open(filepath_obj, "rb") as f:
|
||||
while True:
|
||||
data = f.read(chunk_size)
|
||||
if not data:
|
||||
|
||||
+31
-5
@@ -1,6 +1,7 @@
|
||||
import ipaddress
|
||||
import logging
|
||||
import socket
|
||||
from urllib.parse import urlsplit, urlunsplit
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -27,8 +28,33 @@ def is_private_ip(hostname: str) -> bool:
|
||||
return True
|
||||
return False
|
||||
except (socket.gaierror, socket.error):
|
||||
# Cannot resolve - allow for testing/development
|
||||
# In production, DNS should work properly
|
||||
# Log this for debugging
|
||||
logger.warning(f"Could not resolve hostname: {hostname}")
|
||||
return False # Changed from True to False to allow external domains in tests
|
||||
# Cannot resolve.
|
||||
# Fail securely: block unresolved domains to prevent DNS rebinding
|
||||
# and SSRF bypasses via unresolvable addresses.
|
||||
logger.warning(f"Could not resolve hostname (blocking securely): {hostname}")
|
||||
return True
|
||||
|
||||
|
||||
def join_url(base: str, *parts: str) -> str:
|
||||
"""
|
||||
Safely join a base URL with one or more path parts.
|
||||
|
||||
Uses urllib.parse to correctly handle scheme/netloc/query/fragment so that
|
||||
only the path component is modified. Leading and trailing slashes are
|
||||
stripped from each part before joining, preventing double-slash sequences
|
||||
at segment boundaries without touching the scheme separator or query string.
|
||||
|
||||
Examples:
|
||||
join_url("https://example.com/dav/", "/remote/", "file.pdf")
|
||||
-> "https://example.com/dav/remote/file.pdf"
|
||||
"""
|
||||
parsed = urlsplit(base)
|
||||
# Strip each part once and filter out empty segments; use walrus operator
|
||||
# to avoid calling strip twice per iteration.
|
||||
stripped_parts = [s for p in parts if (s := p.strip("/"))]
|
||||
base_path = parsed.path.rstrip("/")
|
||||
new_path = base_path + "/" + "/".join(stripped_parts) if stripped_parts else base_path
|
||||
# Ensure path is non-empty so the reconstructed URL is valid.
|
||||
if not new_path:
|
||||
new_path = "/"
|
||||
return urlunsplit((parsed.scheme, parsed.netloc, new_path, parsed.query, parsed.fragment))
|
||||
|
||||
@@ -1089,6 +1089,55 @@ SETTING_METADATA = {
|
||||
"required": False,
|
||||
"restart_required": False,
|
||||
},
|
||||
# Storage Providers - Evernote
|
||||
"evernote_enabled": {
|
||||
"category": "Storage Providers",
|
||||
"description": "Enable Evernote as an upload destination. When disabled, no documents will be sent to Evernote even if credentials are configured.",
|
||||
"type": "boolean",
|
||||
"sensitive": False,
|
||||
"required": False,
|
||||
"restart_required": False,
|
||||
},
|
||||
"evernote_auth_token": {
|
||||
"category": "Storage Providers",
|
||||
"description": "Evernote developer token for note creation",
|
||||
"type": "string",
|
||||
"sensitive": True,
|
||||
"required": False,
|
||||
"restart_required": False,
|
||||
},
|
||||
"evernote_sandbox": {
|
||||
"category": "Storage Providers",
|
||||
"description": "Use the Evernote sandbox environment instead of production",
|
||||
"type": "boolean",
|
||||
"sensitive": False,
|
||||
"required": False,
|
||||
"restart_required": False,
|
||||
},
|
||||
"evernote_notebook_guid": {
|
||||
"category": "Storage Providers",
|
||||
"description": "Optional Evernote notebook GUID for uploaded notes",
|
||||
"type": "string",
|
||||
"sensitive": False,
|
||||
"required": False,
|
||||
"restart_required": False,
|
||||
},
|
||||
"evernote_default_tags": {
|
||||
"category": "Storage Providers",
|
||||
"description": "Comma-separated Evernote tags to apply to uploaded notes",
|
||||
"type": "string",
|
||||
"sensitive": False,
|
||||
"required": False,
|
||||
"restart_required": False,
|
||||
},
|
||||
"evernote_include_metadata": {
|
||||
"category": "Storage Providers",
|
||||
"description": "Include extracted document metadata in Evernote note content",
|
||||
"type": "boolean",
|
||||
"sensitive": False,
|
||||
"required": False,
|
||||
"restart_required": False,
|
||||
},
|
||||
# Storage Providers - Google Drive
|
||||
"google_drive_enabled": {
|
||||
"category": "Storage Providers",
|
||||
|
||||
@@ -29,7 +29,7 @@ At average usage (~40 % of quota) margins improve to 55-65 % after tax.
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from datetime import date, datetime, timezone
|
||||
from datetime import date, datetime, time, timedelta, timezone
|
||||
from typing import Any
|
||||
|
||||
from sqlalchemy import func
|
||||
@@ -317,6 +317,20 @@ def _today_utc() -> date:
|
||||
return datetime.now(timezone.utc).date()
|
||||
|
||||
|
||||
def _day_bounds_utc(day: date) -> tuple[datetime, datetime]:
|
||||
start = datetime.combine(day, time.min, tzinfo=timezone.utc)
|
||||
return start, start + timedelta(days=1)
|
||||
|
||||
|
||||
def _month_bounds_utc(day: date) -> tuple[datetime, datetime]:
|
||||
start = datetime.combine(day.replace(day=1), time.min, tzinfo=timezone.utc)
|
||||
if start.month == 12:
|
||||
end = start.replace(year=start.year + 1, month=1)
|
||||
else:
|
||||
end = start.replace(month=start.month + 1)
|
||||
return start, end
|
||||
|
||||
|
||||
def _scalar_count(query: Any) -> int:
|
||||
"""Execute a count query and return an int, defaulting to 0 for NULL."""
|
||||
return query.scalar() or 0
|
||||
@@ -335,12 +349,13 @@ def get_today_file_count(db: Session, owner_id: str) -> int:
|
||||
"""Files processed by this user today (UTC, not counting duplicates)."""
|
||||
from app.models import FileRecord
|
||||
|
||||
today = _today_utc()
|
||||
day_start, day_end = _day_bounds_utc(_today_utc())
|
||||
return _scalar_count(
|
||||
db.query(func.count(FileRecord.id)).filter(
|
||||
FileRecord.owner_id == owner_id,
|
||||
FileRecord.is_duplicate.is_(False),
|
||||
func.date(FileRecord.created_at) == today,
|
||||
FileRecord.created_at >= day_start,
|
||||
FileRecord.created_at < day_end,
|
||||
)
|
||||
)
|
||||
|
||||
@@ -349,12 +364,13 @@ def get_month_file_count(db: Session, owner_id: str) -> int:
|
||||
"""Files processed by this user this calendar month (UTC, not counting duplicates)."""
|
||||
from app.models import FileRecord
|
||||
|
||||
today = _today_utc()
|
||||
month_start, month_end = _month_bounds_utc(_today_utc())
|
||||
return _scalar_count(
|
||||
db.query(func.count(FileRecord.id)).filter(
|
||||
FileRecord.owner_id == owner_id,
|
||||
FileRecord.is_duplicate.is_(False),
|
||||
func.strftime("%Y-%m", FileRecord.created_at) == today.strftime("%Y-%m"),
|
||||
FileRecord.created_at >= month_start,
|
||||
FileRecord.created_at < month_end,
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
@@ -12,11 +12,13 @@ import smtplib
|
||||
from email.mime.multipart import MIMEMultipart
|
||||
from email.mime.text import MIMEText
|
||||
from typing import Any
|
||||
from urllib.parse import urlparse
|
||||
|
||||
import httpx
|
||||
|
||||
from app.database import SessionLocal
|
||||
from app.models import InAppNotification, UserNotificationPreference, UserNotificationTarget
|
||||
from app.utils.network import is_private_ip
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -28,6 +30,11 @@ USER_EVENT_LABELS: dict[str, str] = {
|
||||
EVENT_DOCUMENT_PROCESSED: "Document Processed",
|
||||
EVENT_DOCUMENT_FAILED: "Document Processing Failed",
|
||||
}
|
||||
METADATA_ENDPOINTS = {
|
||||
"169.254.169.254",
|
||||
"169.254.169.253",
|
||||
"metadata.google.internal",
|
||||
}
|
||||
|
||||
|
||||
def create_in_app_notification(
|
||||
@@ -128,6 +135,20 @@ def _send_webhook_notification(target_config: dict[str, Any], event_type: str, t
|
||||
logger.warning("Webhook notification target missing url")
|
||||
return False
|
||||
|
||||
parsed_url = urlparse(url)
|
||||
if parsed_url.scheme not in {"http", "https"}:
|
||||
logger.warning("Webhook notification to %s blocked: invalid scheme %s", url, parsed_url.scheme)
|
||||
return False
|
||||
|
||||
hostname = parsed_url.hostname
|
||||
if not hostname:
|
||||
logger.warning("Webhook notification to %s blocked: missing hostname", url)
|
||||
return False
|
||||
|
||||
if hostname in METADATA_ENDPOINTS or is_private_ip(hostname):
|
||||
logger.warning("Webhook notification to %s blocked: private or metadata endpoint", url)
|
||||
return False
|
||||
|
||||
payload = {
|
||||
"event": event_type,
|
||||
"title": title,
|
||||
|
||||
@@ -18,11 +18,13 @@ import json
|
||||
import logging
|
||||
import time
|
||||
from typing import Any
|
||||
from urllib.parse import urlparse
|
||||
|
||||
import requests
|
||||
|
||||
from app.database import SessionLocal
|
||||
from app.models import WebhookConfig
|
||||
from app.utils.network import is_private_ip
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -40,6 +42,11 @@ VALID_EVENTS: frozenset[str] = frozenset(
|
||||
|
||||
#: Timeout (seconds) for outgoing webhook HTTP requests.
|
||||
WEBHOOK_TIMEOUT = 10
|
||||
METADATA_ENDPOINTS = {
|
||||
"169.254.169.254",
|
||||
"169.254.169.253",
|
||||
"metadata.google.internal",
|
||||
}
|
||||
|
||||
|
||||
def compute_signature(payload_bytes: bytes, secret: str) -> str:
|
||||
@@ -67,6 +74,20 @@ def deliver_webhook(url: str, payload: dict[str, Any], secret: str | None = None
|
||||
Returns:
|
||||
``True`` when the remote server responds with a 2xx status.
|
||||
"""
|
||||
parsed_url = urlparse(url)
|
||||
if parsed_url.scheme not in {"http", "https"}:
|
||||
logger.warning("Webhook to %s blocked: invalid scheme %s", url, parsed_url.scheme)
|
||||
return False
|
||||
|
||||
hostname = parsed_url.hostname
|
||||
if not hostname:
|
||||
logger.warning("Webhook to %s blocked: missing hostname", url)
|
||||
return False
|
||||
|
||||
if hostname in METADATA_ENDPOINTS or is_private_ip(hostname):
|
||||
logger.warning("Webhook to %s blocked: private or metadata endpoint", url)
|
||||
return False
|
||||
|
||||
body = json.dumps(payload, default=str, sort_keys=True)
|
||||
body_bytes = body.encode("utf-8")
|
||||
|
||||
|
||||
+29
-5
@@ -162,12 +162,36 @@ def _inject_global_context(ctx: dict) -> None:
|
||||
|
||||
|
||||
def template_response_with_version(*args, **kwargs):
|
||||
"""Wrapper for TemplateResponse to include version and CSRF token in all templates"""
|
||||
# If context dict is provided, add version to it
|
||||
if len(args) >= 2 and isinstance(args[1], dict):
|
||||
_inject_global_context(args[1])
|
||||
elif "context" in kwargs and isinstance(kwargs["context"], dict):
|
||||
"""Wrapper for TemplateResponse to include version and CSRF token in all templates.
|
||||
|
||||
Handles both old-style and new-style Starlette TemplateResponse calls:
|
||||
- Old-style (Starlette <1.0): TemplateResponse(name, {"request": req, ...}, ...)
|
||||
- New-style (Starlette 1.0+): TemplateResponse(request, name, context={...}, ...)
|
||||
"""
|
||||
if len(args) >= 1 and isinstance(args[0], str):
|
||||
# Old-style call: first positional arg is the template name (string).
|
||||
# Convert to new-style: (request, name, context=..., ...)
|
||||
name = args[0]
|
||||
if len(args) >= 2 and isinstance(args[1], dict):
|
||||
context = args[1]
|
||||
# Old-style may have status_code as 3rd positional arg
|
||||
if len(args) >= 3 and "status_code" not in kwargs:
|
||||
kwargs["status_code"] = args[2]
|
||||
else:
|
||||
context = kwargs.pop("context", {})
|
||||
request_obj = context.pop("request", None)
|
||||
if request_obj is not None:
|
||||
context["request"] = request_obj
|
||||
_inject_global_context(context)
|
||||
if request_obj is not None:
|
||||
return original_template_response(request_obj, name, context=context, **kwargs)
|
||||
return original_template_response(name, context=context, **kwargs)
|
||||
|
||||
# New-style call: (request, name, context=..., ...)
|
||||
if "context" in kwargs and isinstance(kwargs["context"], dict):
|
||||
_inject_global_context(kwargs["context"])
|
||||
elif len(args) >= 3 and isinstance(args[2], dict):
|
||||
_inject_global_context(args[2])
|
||||
return original_template_response(*args, **kwargs)
|
||||
|
||||
|
||||
|
||||
@@ -717,6 +717,7 @@ def _compute_processing_flow(logs, pipeline_steps=None):
|
||||
"upload_to_ftp": "FTP Storage",
|
||||
"upload_to_sftp": "SFTP Storage",
|
||||
"upload_to_email": "Email",
|
||||
"upload_to_evernote": "Evernote",
|
||||
"queue_dropbox": "Dropbox",
|
||||
"queue_nextcloud": "Nextcloud",
|
||||
"queue_paperless": "Paperless-ngx",
|
||||
@@ -727,6 +728,7 @@ def _compute_processing_flow(logs, pipeline_steps=None):
|
||||
"queue_ftp": "FTP Storage",
|
||||
"queue_sftp": "SFTP Storage",
|
||||
"queue_email": "Email",
|
||||
"queue_evernote": "Evernote",
|
||||
}
|
||||
|
||||
# Create a map of step names to their log entries
|
||||
|
||||
+13
-3
@@ -2,7 +2,7 @@
|
||||
General routes for the application homepage and basic pages.
|
||||
"""
|
||||
|
||||
from datetime import date, datetime, timezone
|
||||
from datetime import date, datetime, time, timedelta, timezone
|
||||
from pathlib import Path
|
||||
|
||||
from fastapi import Depends, HTTPException, Request
|
||||
@@ -64,17 +64,27 @@ async def serve_index(request: Request, db: Session = Depends(get_db)):
|
||||
|
||||
user = request.session.get("user") or {}
|
||||
is_admin = user.get("is_admin", False)
|
||||
day_start = datetime.combine(today, time.min, tzinfo=timezone.utc)
|
||||
day_end = day_start + timedelta(days=1)
|
||||
month_start = day_start.replace(day=1)
|
||||
if month_start.month == 12:
|
||||
month_end = month_start.replace(year=month_start.year + 1, month=1)
|
||||
else:
|
||||
month_end = month_start.replace(month=month_start.month + 1)
|
||||
|
||||
try:
|
||||
total_files: int = db.query(func.count(FileRecord.id)).scalar() or 0
|
||||
|
||||
files_today: int = (
|
||||
db.query(func.count(FileRecord.id)).filter(func.date(FileRecord.created_at) == today).scalar() or 0
|
||||
db.query(func.count(FileRecord.id))
|
||||
.filter(FileRecord.created_at >= day_start, FileRecord.created_at < day_end)
|
||||
.scalar()
|
||||
or 0
|
||||
)
|
||||
|
||||
files_month: int = (
|
||||
db.query(func.count(FileRecord.id))
|
||||
.filter(func.strftime("%Y-%m", FileRecord.created_at) == today.strftime("%Y-%m"))
|
||||
.filter(FileRecord.created_at >= month_start, FileRecord.created_at < month_end)
|
||||
.scalar()
|
||||
or 0
|
||||
)
|
||||
|
||||
+2
-1
@@ -23,6 +23,7 @@ templates = Jinja2Templates(directory=str(_templates_dir))
|
||||
async def shared_link_view(request: Request, token: str):
|
||||
"""Render the public share landing page for a given token."""
|
||||
return templates.TemplateResponse(
|
||||
request,
|
||||
"shared_link_view.html",
|
||||
{"request": request, "token": token},
|
||||
context={"token": token},
|
||||
)
|
||||
|
||||
+4
-25
@@ -3,7 +3,7 @@ services:
|
||||
build:
|
||||
context: .
|
||||
dockerfile: Dockerfile
|
||||
# No container_name — allows `docker compose up --scale api=N`
|
||||
container_name: document_api
|
||||
restart: always
|
||||
|
||||
# We'll keep the code in /app, but set working_dir to the shared data directory
|
||||
@@ -24,7 +24,7 @@ services:
|
||||
|
||||
depends_on:
|
||||
- redis
|
||||
- beat
|
||||
- worker
|
||||
|
||||
# Mount the shared working directory for data
|
||||
volumes:
|
||||
@@ -34,14 +34,13 @@ services:
|
||||
build:
|
||||
context: .
|
||||
dockerfile: Dockerfile
|
||||
# No container_name — allows `docker compose up --scale worker=N`
|
||||
container_name: document_worker
|
||||
restart: always
|
||||
|
||||
# same shared working directory
|
||||
working_dir: /workdir
|
||||
|
||||
# Workers process tasks only — no -B flag (Beat runs in the dedicated beat service)
|
||||
command: ["celery", "-A", "app.celery_worker", "worker", "--loglevel=info", "-Q", "document_processor,default,celery"]
|
||||
command: ["celery", "-A", "app.celery_worker", "worker", "-B", "--loglevel=info", "-Q", "document_processor,default,celery"]
|
||||
env_file:
|
||||
- .env
|
||||
environment:
|
||||
@@ -55,26 +54,6 @@ services:
|
||||
volumes:
|
||||
- /var/docparse/workdir:/workdir
|
||||
|
||||
# Dedicated Celery Beat scheduler — exactly one instance must run at all times.
|
||||
# Beat publishes periodic tasks to the Redis broker; workers pick them up.
|
||||
# Do NOT scale this service (replicas must stay at 1).
|
||||
beat:
|
||||
build:
|
||||
context: .
|
||||
dockerfile: Dockerfile
|
||||
container_name: document_beat
|
||||
restart: always
|
||||
working_dir: /workdir
|
||||
command: ["celery", "-A", "app.celery_worker", "beat", "--loglevel=info"]
|
||||
env_file:
|
||||
- .env
|
||||
environment:
|
||||
- PYTHONPATH=/app
|
||||
depends_on:
|
||||
- redis
|
||||
volumes:
|
||||
- /var/docparse/workdir:/workdir
|
||||
|
||||
gotenberg:
|
||||
image: gotenberg/gotenberg:latest
|
||||
container_name: gotenberg
|
||||
|
||||
@@ -792,7 +792,7 @@ SECURITY_HEADER_CSP_VALUE="default-src 'self'; script-src 'self'; style-src 'sel
|
||||
SECURITY_HEADER_CSP_VALUE="default-src 'self'; script-src 'self' https://cdn.example.com; style-src 'self' 'unsafe-inline';"
|
||||
```
|
||||
|
||||
**Note:** The default policy includes `'unsafe-inline'` for compatibility with Tailwind CSS and inline JavaScript. For stricter security, use nonces or hashes.
|
||||
**Note:** The default policy includes `'unsafe-inline'` for compatibility with inline JavaScript. Tailwind CSS v3 is compiled at build time into a static file served from `'self'`, so no external style CDN is needed.
|
||||
|
||||
#### X-Frame-Options
|
||||
|
||||
@@ -1330,6 +1330,19 @@ For detailed setup instructions, see the [Google Drive Setup Guide](GoogleDriveS
|
||||
| `DEST_EMAIL_SENDER` | From address for delivered documents (e.g., `"DocuElevate Delivery <docuelevate@example.com>"`). |
|
||||
| `DEST_EMAIL_DEFAULT_RECIPIENT` | Fallback recipient email when none is specified for a delivery task. |
|
||||
|
||||
### Evernote
|
||||
|
||||
| **Variable** | **Description** |
|
||||
|-------------------------------|---------------------------------------------------------------------|
|
||||
| `EVERNOTE_ENABLED` | Set to `false` to disable Evernote uploads without removing credentials. Default: `true` |
|
||||
| `EVERNOTE_AUTH_TOKEN` | Evernote developer token or OAuth access token used to create notes. |
|
||||
| `EVERNOTE_SANDBOX` | Use Evernote sandbox API endpoints. Default: `false` |
|
||||
| `EVERNOTE_NOTEBOOK_GUID` | Optional target notebook GUID. If omitted, Evernote uses the default notebook. |
|
||||
| `EVERNOTE_DEFAULT_TAGS` | Optional comma-separated tags applied to every created note. |
|
||||
| `EVERNOTE_INCLUDE_METADATA` | Include extracted metadata in the Evernote note body. Default: `true` |
|
||||
|
||||
For detailed setup instructions, see the [Evernote Setup Guide](EvernoteSetup.md).
|
||||
|
||||
### OneDrive / Microsoft Graph
|
||||
|
||||
| **Variable** | **Description** |
|
||||
|
||||
@@ -13,6 +13,7 @@ DocuElevate is designed to be highly configurable through environment variables,
|
||||
- [Dropbox Setup](DropboxSetup.md) - How to set up Dropbox integration
|
||||
- [OneDrive Setup](OneDriveSetup.md) - How to set up Microsoft OneDrive/Graph integration
|
||||
- [Amazon S3 Setup](AmazonS3Setup.md) - How to set up Amazon S3 integration
|
||||
- [Evernote Setup](EvernoteSetup.md) - How to set up Evernote note creation
|
||||
- [Authentication Setup](AuthenticationSetup.md) - How to set up user authentication
|
||||
- [Notifications Setup](NotificationsSetup.md) - How to set up system notifications
|
||||
|
||||
|
||||
@@ -0,0 +1,51 @@
|
||||
# Setting up Evernote Integration
|
||||
|
||||
This guide explains how to configure DocuElevate to create Evernote notes for processed documents.
|
||||
|
||||
## Overview
|
||||
|
||||
The Evernote destination creates one note per processed document. The note contains:
|
||||
|
||||
- A visible metadata section populated from DocuElevate's extracted metadata JSON
|
||||
- The processed PDF attached as an Evernote resource
|
||||
- Optional tags from `EVERNOTE_DEFAULT_TAGS` plus extracted document tags
|
||||
|
||||
## Required Configuration
|
||||
|
||||
| Variable | Description |
|
||||
|----------|-------------|
|
||||
| `EVERNOTE_ENABLED` | Set to `false` to disable Evernote uploads without removing credentials. Default: `true` |
|
||||
| `EVERNOTE_AUTH_TOKEN` | Evernote developer token or OAuth access token with note creation permissions |
|
||||
|
||||
## Optional Configuration
|
||||
|
||||
| Variable | Description |
|
||||
|----------|-------------|
|
||||
| `EVERNOTE_SANDBOX` | Use Evernote sandbox API endpoints. Default: `false` |
|
||||
| `EVERNOTE_NOTEBOOK_GUID` | Target notebook GUID. If omitted, Evernote uses the account default notebook |
|
||||
| `EVERNOTE_DEFAULT_TAGS` | Comma-separated tags to apply to every created note, for example `docuelevate,archive` |
|
||||
| `EVERNOTE_INCLUDE_METADATA` | Include extracted metadata in the note body. Default: `true` |
|
||||
|
||||
## Example
|
||||
|
||||
```dotenv
|
||||
EVERNOTE_ENABLED=true
|
||||
EVERNOTE_AUTH_TOKEN=your-evernote-token
|
||||
EVERNOTE_NOTEBOOK_GUID=optional-notebook-guid
|
||||
EVERNOTE_DEFAULT_TAGS=docuelevate,processed
|
||||
EVERNOTE_INCLUDE_METADATA=true
|
||||
```
|
||||
|
||||
## Metadata and Attachments
|
||||
|
||||
DocuElevate reads the companion metadata file next to the processed PDF, for example `invoice.pdf` and `invoice.json`. Non-empty metadata fields are rendered into the Evernote note body. Values such as `Unknown`, empty strings, and null values are skipped.
|
||||
|
||||
If the metadata contains a `tags` field, those tags are applied to the note together with any tags configured in `EVERNOTE_DEFAULT_TAGS`.
|
||||
|
||||
The processed PDF is attached directly to the note using Evernote's resource model, so it appears as a normal Evernote attachment.
|
||||
|
||||
## Notes
|
||||
|
||||
- Evernote tokens can expire or be revoked. If uploads start failing with authentication errors, generate or refresh the token and update `EVERNOTE_AUTH_TOKEN`.
|
||||
- If `EVERNOTE_NOTEBOOK_GUID` points to a missing or inaccessible notebook, Evernote will reject the note creation request.
|
||||
- Evernote enforces account upload quotas and per-note size limits. Large PDFs may fail if they exceed those limits.
|
||||
@@ -157,7 +157,7 @@ Recommended headers to configure at the proxy level:
|
||||
|
||||
#### Content-Security-Policy Notes
|
||||
|
||||
DocuElevate's frontend uses Tailwind CSS loaded from CDN in development mode. In production, ensure your CSP allows loading scripts and styles from your configured static file origin. A starting point:
|
||||
DocuElevate's frontend uses Tailwind CSS v3 compiled at Docker build time. No external CDN requests are needed for CSS. In production, your CSP does not need to allow any external style sources beyond your own static file origin. A starting point:
|
||||
|
||||
```
|
||||
Content-Security-Policy: default-src 'self'; script-src 'self' 'unsafe-inline'; style-src 'self' 'unsafe-inline'; img-src 'self' data:;
|
||||
|
||||
@@ -24,6 +24,7 @@ Welcome to the DocuElevate documentation. This directory contains comprehensive
|
||||
- [OneDrive Setup](OneDriveSetup.md) - How to set up Microsoft OneDrive/Graph integration
|
||||
- [SharePoint Setup](SharePointSetup.md) - How to set up Microsoft SharePoint Online integration
|
||||
- [Amazon S3 Setup](AmazonS3Setup.md) - How to set up Amazon S3 integration
|
||||
- [Evernote Setup](EvernoteSetup.md) - How to set up Evernote note creation
|
||||
- [Authentication Setup](AuthenticationSetup.md) - How to set up user authentication
|
||||
- [Notifications Setup](NotificationsSetup.md) - How to set up system notifications
|
||||
|
||||
|
||||
@@ -28,7 +28,7 @@ Settings are organized into logical categories for easy navigation:
|
||||
- **Authentication**: Login settings, session secrets, OAuth configuration, admin group
|
||||
- **AI Services**: AI provider selection, model configuration, embeddings, and credentials (OpenAI, Azure, Anthropic, Gemini, Ollama, OpenRouter, Portkey, LiteLLM)
|
||||
- **OCR Engines**: OCR provider selection and configuration (Tesseract, EasyOCR, Mistral, Google DocAI, AWS Textract)
|
||||
- **Storage Providers**: Dropbox, Google Drive, OneDrive, SharePoint, S3, FTP, SFTP, WebDAV, Nextcloud, Paperless
|
||||
- **Storage Providers**: Dropbox, Google Drive, OneDrive, SharePoint, S3, FTP, SFTP, WebDAV, Nextcloud, Paperless, Evernote
|
||||
- **Email**: SMTP configuration for sending emails
|
||||
- **IMAP**: Email ingestion configuration (supports two mailbox accounts)
|
||||
- **Monitoring**: Uptime Kuma integration
|
||||
|
||||
@@ -125,6 +125,7 @@ Several cloud storage integrations include their own guided configuration pages
|
||||
| Google Drive | `/google-drive-setup` | [GoogleDriveSetup.md](GoogleDriveSetup.md) |
|
||||
| OneDrive / SharePoint | `/onedrive-setup` | [OneDriveSetup.md](OneDriveSetup.md) |
|
||||
| Amazon S3 | Configured via settings | [AmazonS3Setup.md](AmazonS3Setup.md) |
|
||||
| Evernote | Configured via settings | [EvernoteSetup.md](EvernoteSetup.md) |
|
||||
|
||||
These pages are accessed **after** the main Setup Wizard is complete and are independent wizard flows specific to each integration.
|
||||
|
||||
|
||||
@@ -0,0 +1,329 @@
|
||||
/* frontend/input.css
|
||||
* Tailwind CSS v3 source file.
|
||||
* Edit this file (not static/styles.css) — the compiled output is
|
||||
* generated by running: npm run build (inside the frontend/ directory)
|
||||
*/
|
||||
|
||||
/* ── Tailwind layers ──────────────────────────────────────────────────────── */
|
||||
@tailwind base;
|
||||
@tailwind components;
|
||||
@tailwind utilities;
|
||||
|
||||
/* ── Custom utilities ─────────────────────────────────────────────────────── */
|
||||
|
||||
/* =============================================================
|
||||
ACCESSIBILITY
|
||||
Skip-to-content link, focus indicators, and screen-reader-only
|
||||
utility class following WCAG 2.1 Level AA requirements.
|
||||
============================================================= */
|
||||
|
||||
/* Skip-to-content link: visible only on keyboard focus */
|
||||
.skip-link {
|
||||
position: absolute;
|
||||
left: -9999px;
|
||||
top: auto;
|
||||
width: 1px;
|
||||
height: 1px;
|
||||
overflow: hidden;
|
||||
z-index: 9999;
|
||||
padding: 0.75rem 1.5rem;
|
||||
background-color: #1d4ed8;
|
||||
color: #ffffff;
|
||||
font-weight: 600;
|
||||
text-decoration: none;
|
||||
border-radius: 0 0 0.375rem 0;
|
||||
}
|
||||
.skip-link:focus {
|
||||
position: fixed;
|
||||
top: 0;
|
||||
left: 0;
|
||||
width: auto;
|
||||
height: auto;
|
||||
outline: 2px solid #2563eb;
|
||||
outline-offset: 2px;
|
||||
}
|
||||
|
||||
/* Enhanced focus-visible indicators for keyboard navigation (WCAG 2.4.7) */
|
||||
a:focus-visible,
|
||||
button:focus-visible,
|
||||
input:focus-visible,
|
||||
select:focus-visible,
|
||||
textarea:focus-visible,
|
||||
[tabindex]:focus-visible {
|
||||
outline: 2px solid #2563eb;
|
||||
outline-offset: 2px;
|
||||
}
|
||||
|
||||
/* Screen-reader-only utility (visually hidden, accessible to AT) */
|
||||
.sr-only {
|
||||
position: absolute;
|
||||
width: 1px;
|
||||
height: 1px;
|
||||
padding: 0;
|
||||
margin: -1px;
|
||||
overflow: hidden;
|
||||
clip: rect(0, 0, 0, 0);
|
||||
white-space: nowrap;
|
||||
border-width: 0;
|
||||
}
|
||||
|
||||
body {
|
||||
/* Your global overrides can go here if needed */
|
||||
}
|
||||
.material-symbols-light--folder-managed-outline {
|
||||
display: inline-block;
|
||||
width: 96px;
|
||||
height: 96px;
|
||||
--svg: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 24 24'%3E%3Cpath fill='%23000' d='m17.212 20.404l-.108-.885q-.57-.125-.938-.33q-.368-.204-.7-.577l-.835.334l-.539-.815l.689-.577q-.165-.531-.165-1.035t.165-1.034l-.689-.577l.539-.816l.835.335q.332-.393.7-.588q.369-.195.938-.32l.108-.885h1l.107.885q.57.125.938.32t.7.588l.835-.335l.539.816l-.689.576q.166.531.166 1.035t-.166 1.035l.689.577l-.539.815l-.834-.335q-.333.373-.701.578q-.369.205-.938.33l-.107.885zm.5-1.731q.882 0 1.518-.635q.636-.636.636-1.519t-.636-1.518t-1.518-.636t-1.519.636t-.635 1.518t.635 1.519t1.518.635M4 18V6v4.435V10zm.616 1q-.691 0-1.153-.462T3 17.384V6.616q0-.691.463-1.153T4.615 5h4.981l2 2h7.789q.69 0 1.153.463T21 8.616v2.294q-.238-.152-.479-.265q-.24-.112-.521-.21v-1.82q0-.269-.173-.442T19.385 8h-8.19l-2-2h-4.58q-.269 0-.442.173T4 6.616v10.769q0 .269.173.442t.443.173h6.748q.055.275.131.515t.186.485z'/%3E%3C/svg%3E");
|
||||
background-color: currentColor;
|
||||
-webkit-mask-image: var(--svg);
|
||||
mask-image: var(--svg);
|
||||
-webkit-mask-repeat: no-repeat;
|
||||
mask-repeat: no-repeat;
|
||||
-webkit-mask-size: 100% 100%;
|
||||
mask-size: 100% 100%;
|
||||
}
|
||||
|
||||
/* Ensure pagination wraps properly on small screens */
|
||||
.pagination {
|
||||
flex-wrap: wrap;
|
||||
gap: 0.5rem;
|
||||
}
|
||||
.pagination-buttons {
|
||||
flex-wrap: wrap;
|
||||
}
|
||||
|
||||
/* Ensure filter items stack on very small screens */
|
||||
@media (max-width: 480px) {
|
||||
.filter-group {
|
||||
flex-direction: column;
|
||||
}
|
||||
.filter-item {
|
||||
min-width: unset;
|
||||
width: 100%;
|
||||
}
|
||||
}
|
||||
|
||||
/* =============================================================
|
||||
DARK MODE
|
||||
Activated by "dark" class on <html> element.
|
||||
Toggled by the navbar button; preference stored in localStorage.
|
||||
Falls back to the server-side ui_default_color_scheme setting,
|
||||
then to the OS prefers-color-scheme media query.
|
||||
WCAG AA contrast ratios verified for all text/background pairs.
|
||||
============================================================= */
|
||||
|
||||
/* Tell the browser we support both colour schemes */
|
||||
html { color-scheme: light; }
|
||||
html.dark { color-scheme: dark; }
|
||||
|
||||
/* ---- Base / Body ---- */
|
||||
html.dark body { background-color: #111827; color: #e5e7eb; }
|
||||
html.dark .bg-gray-50 { background-color: #111827; }
|
||||
html.dark .bg-white { background-color: #1f2937; }
|
||||
html.dark .bg-gray-100 { background-color: #374151; }
|
||||
html.dark .bg-gray-200 { background-color: #4b5563; }
|
||||
|
||||
/* ---- Text colours ---- */
|
||||
html.dark .text-gray-900 { color: #f9fafb; }
|
||||
html.dark .text-gray-800 { color: #f3f4f6; }
|
||||
html.dark .text-gray-700 { color: #e5e7eb; }
|
||||
html.dark .text-gray-600 { color: #d1d5db; }
|
||||
html.dark .text-gray-500 { color: #9ca3af; }
|
||||
html.dark .text-gray-400 { color: #9ca3af; }
|
||||
html.dark .text-black { color: #f9fafb; }
|
||||
|
||||
/* ---- Borders ---- */
|
||||
html.dark .border-gray-100 { border-color: #374151; }
|
||||
html.dark .border-gray-200 { border-color: #374151; }
|
||||
html.dark .border-gray-300 { border-color: #4b5563; }
|
||||
html.dark .border-gray-400 { border-color: #6b7280; }
|
||||
html.dark .divide-gray-200 > :not([hidden]) ~ :not([hidden]) { border-color: #374151; }
|
||||
html.dark .divide-gray-100 > :not([hidden]) ~ :not([hidden]) { border-color: #374151; }
|
||||
html.dark .divide-y > :not([hidden]) ~ :not([hidden]) { border-color: #374151; }
|
||||
|
||||
/* ---- Hover states ---- */
|
||||
html.dark .hover\:bg-gray-50:hover { background-color: #374151; }
|
||||
html.dark .hover\:bg-gray-100:hover { background-color: #4b5563; }
|
||||
html.dark .hover\:text-gray-900:hover { color: #f9fafb; }
|
||||
html.dark .hover\:text-gray-700:hover { color: #e5e7eb; }
|
||||
|
||||
/* ---- Shadows (softened for dark mode) ---- */
|
||||
html.dark .shadow,
|
||||
html.dark .shadow-md,
|
||||
html.dark .shadow-sm,
|
||||
html.dark .shadow-lg {
|
||||
box-shadow: 0 1px 3px 0 rgba(0,0,0,0.6), 0 1px 2px 0 rgba(0,0,0,0.4);
|
||||
}
|
||||
|
||||
/* ---- Alert / info-banner backgrounds ---- */
|
||||
html.dark .bg-blue-50 { background-color: #1e3a5f; }
|
||||
html.dark .bg-green-50 { background-color: #052e16; }
|
||||
html.dark .bg-red-50 { background-color: #450a0a; }
|
||||
html.dark .bg-yellow-50 { background-color: #451a03; }
|
||||
html.dark .bg-indigo-50 { background-color: #1e1b4b; }
|
||||
html.dark .bg-orange-50 { background-color: #431407; }
|
||||
|
||||
/* ---- Badge / pill backgrounds ---- */
|
||||
html.dark .bg-blue-100 { background-color: #1e3a5f; }
|
||||
html.dark .bg-green-100 { background-color: #052e16; }
|
||||
html.dark .bg-red-100 { background-color: #450a0a; }
|
||||
html.dark .bg-yellow-100 { background-color: #451a03; }
|
||||
html.dark .bg-indigo-100 { background-color: #431407; }
|
||||
html.dark .bg-orange-100 { background-color: #431407; }
|
||||
html.dark .bg-purple-100 { background-color: #2e1065; }
|
||||
|
||||
/* ---- Status / badge text colours ---- */
|
||||
html.dark .text-blue-700 { color: #93c5fd; }
|
||||
html.dark .text-blue-800 { color: #bfdbfe; }
|
||||
html.dark .text-green-700 { color: #86efac; }
|
||||
html.dark .text-green-800 { color: #bbf7d0; }
|
||||
html.dark .text-red-700 { color: #fca5a5; }
|
||||
html.dark .text-red-800 { color: #fecaca; }
|
||||
html.dark .text-yellow-700 { color: #fcd34d; }
|
||||
html.dark .text-yellow-800 { color: #fde68a; }
|
||||
html.dark .text-indigo-700 { color: #a5b4fc; }
|
||||
html.dark .text-indigo-800 { color: #c7d2fe; }
|
||||
html.dark .text-orange-700 { color: #fdba74; }
|
||||
html.dark .text-orange-800 { color: #fed7aa; }
|
||||
html.dark .text-purple-700 { color: #d8b4fe; }
|
||||
html.dark .text-purple-800 { color: #e9d5ff; }
|
||||
|
||||
/* ---- Dropdown / popup menus ---- */
|
||||
html.dark .bg-white.rounded-md.shadow-lg { background-color: #1f2937; }
|
||||
html.dark .ring-black { --tw-ring-color: rgba(0,0,0,0.5); }
|
||||
|
||||
/* ---- Form inputs / selects / textareas ---- */
|
||||
html.dark input:not([type="checkbox"]):not([type="radio"]):not([type="range"]),
|
||||
html.dark select,
|
||||
html.dark textarea {
|
||||
background-color: #374151;
|
||||
border-color: #4b5563;
|
||||
color: #e5e7eb;
|
||||
}
|
||||
html.dark input::placeholder,
|
||||
html.dark textarea::placeholder {
|
||||
color: #9ca3af;
|
||||
}
|
||||
html.dark input:focus:not([type="checkbox"]):not([type="radio"]):not([type="range"]),
|
||||
html.dark select:focus,
|
||||
html.dark textarea:focus {
|
||||
border-color: #60a5fa;
|
||||
outline-color: #60a5fa;
|
||||
}
|
||||
|
||||
/* ---- Table rows ---- */
|
||||
html.dark thead,
|
||||
html.dark .bg-gray-50 thead { background-color: #1f2937; }
|
||||
html.dark thead th { color: #9ca3af; }
|
||||
html.dark tbody tr:hover { background-color: #374151; }
|
||||
|
||||
/* ---- Code / pre ---- */
|
||||
html.dark pre,
|
||||
html.dark code { background-color: #111827; color: #d1d5db; }
|
||||
|
||||
/* ---- Dark-mode toggle button icon colour ---- */
|
||||
html.dark #darkModeToggle { color: #fbbf24; }
|
||||
html.dark #darkModeToggle:hover { background-color: #374151; }
|
||||
|
||||
/* ---- Dark-mode skip-link ---- */
|
||||
html.dark .skip-link { background-color: #2563eb; }
|
||||
html.dark .skip-link:focus { outline-color: #60a5fa; }
|
||||
|
||||
/* ---- Dark-mode focus-visible indicators ---- */
|
||||
html.dark a:focus-visible,
|
||||
html.dark button:focus-visible,
|
||||
html.dark input:focus-visible,
|
||||
html.dark select:focus-visible,
|
||||
html.dark textarea:focus-visible,
|
||||
html.dark [tabindex]:focus-visible {
|
||||
outline-color: #60a5fa;
|
||||
}
|
||||
|
||||
/* ---- Scrollbar (WebKit browsers) ---- */
|
||||
html.dark ::-webkit-scrollbar { width: 8px; height: 8px; }
|
||||
html.dark ::-webkit-scrollbar-track { background: #1f2937; }
|
||||
html.dark ::-webkit-scrollbar-thumb { background: #4b5563; border-radius: 4px; }
|
||||
html.dark ::-webkit-scrollbar-thumb:hover { background: #6b7280; }
|
||||
|
||||
/* ---- Settings page: sidebar active state (dark) ---- */
|
||||
html.dark .bg-blue-50 { background-color: #1e3a5f; }
|
||||
|
||||
/* =============================================================
|
||||
DOC-TOGGLE – cross-browser toggle switch
|
||||
Implemented with custom CSS pseudo-elements so the appearance
|
||||
is consistent across all browsers regardless of Tailwind version.
|
||||
Usage:
|
||||
<label class="doc-toggle">
|
||||
<input type="checkbox" class="sr-only" onchange="...">
|
||||
<span class="doc-toggle-track" aria-hidden="true"></span>
|
||||
<span class="ml-3 ...">Label text</span>
|
||||
</label>
|
||||
============================================================= */
|
||||
|
||||
.doc-toggle {
|
||||
position: relative;
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
cursor: pointer;
|
||||
}
|
||||
|
||||
.doc-toggle-track {
|
||||
position: relative;
|
||||
display: inline-block;
|
||||
width: 44px;
|
||||
min-width: 44px;
|
||||
height: 24px;
|
||||
background-color: #e5e7eb; /* gray-200 */
|
||||
border-radius: 9999px;
|
||||
transition: background-color 0.2s ease-in-out;
|
||||
flex-shrink: 0;
|
||||
}
|
||||
|
||||
.doc-toggle-track::after {
|
||||
content: '';
|
||||
position: absolute;
|
||||
top: 2px;
|
||||
left: 2px;
|
||||
width: 20px;
|
||||
height: 20px;
|
||||
background-color: #ffffff;
|
||||
border: 1px solid #d1d5db; /* gray-300 */
|
||||
border-radius: 9999px;
|
||||
transition: transform 0.2s ease-in-out, border-color 0.2s ease-in-out;
|
||||
}
|
||||
|
||||
.doc-toggle input[type="checkbox"]:checked + .doc-toggle-track {
|
||||
background-color: #4f46e5; /* indigo-600 */
|
||||
}
|
||||
|
||||
.doc-toggle input[type="checkbox"]:checked + .doc-toggle-track::after {
|
||||
transform: translateX(20px);
|
||||
border-color: #ffffff;
|
||||
}
|
||||
|
||||
.doc-toggle input[type="checkbox"]:focus-visible + .doc-toggle-track {
|
||||
box-shadow: 0 0 0 2px #ffffff, 0 0 0 4px #6366f1; /* ring-2 ring-indigo-500 with offset */
|
||||
}
|
||||
|
||||
/* Dark mode overrides */
|
||||
html.dark .doc-toggle-track {
|
||||
background-color: #374151; /* gray-700 */
|
||||
}
|
||||
|
||||
html.dark .doc-toggle-track::after {
|
||||
background-color: #ffffff;
|
||||
border-color: #4b5563; /* gray-600 */
|
||||
}
|
||||
|
||||
html.dark .doc-toggle input[type="checkbox"]:checked + .doc-toggle-track {
|
||||
background-color: #4f46e5; /* indigo-600 */
|
||||
}
|
||||
|
||||
html.dark .doc-toggle input[type="checkbox"]:checked + .doc-toggle-track::after {
|
||||
border-color: #ffffff;
|
||||
}
|
||||
|
||||
html.dark .doc-toggle input[type="checkbox"]:focus-visible + .doc-toggle-track {
|
||||
box-shadow: 0 0 0 2px #111827, 0 0 0 4px #6366f1; /* dark background offset */
|
||||
}
|
||||
Generated
+1017
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"name": "docuelevate-frontend",
|
||||
"version": "1.0.0",
|
||||
"description": "Frontend asset compilation for DocuElevate",
|
||||
"scripts": {
|
||||
"build": "tailwindcss -i input.css -o static/styles.css --minify",
|
||||
"watch": "tailwindcss -i input.css -o static/styles.css --watch"
|
||||
},
|
||||
"devDependencies": {
|
||||
"tailwindcss": "^3.4.0"
|
||||
}
|
||||
}
|
||||
@@ -293,13 +293,24 @@ function processFiles(files, progressContainer, statusMessage) {
|
||||
updateStatus();
|
||||
}
|
||||
|
||||
function _escapeHtml(str) {
|
||||
if (!str) return '';
|
||||
return String(str)
|
||||
.replace(/&/g, '&')
|
||||
.replace(/</g, '<')
|
||||
.replace(/>/g, '>')
|
||||
.replace(/"/g, '"')
|
||||
.replace(/'/g, ''');
|
||||
}
|
||||
|
||||
// Pre-create one progress row per file.
|
||||
const queueItems = fileArray.map((file) => {
|
||||
const row = document.createElement('div');
|
||||
row.className = 'flex flex-col mb-2';
|
||||
const safeFileName = _escapeHtml(file.name);
|
||||
row.innerHTML = `
|
||||
<div class="flex justify-between">
|
||||
<span class="text-sm truncate" title="${file.name}">${file.name}</span>
|
||||
<span class="text-sm truncate" title="${safeFileName}">${safeFileName}</span>
|
||||
<span class="text-xs text-gray-500">${formatFileSize(file.size)}</span>
|
||||
</div>
|
||||
<div class="w-full bg-gray-200 h-2 rounded-full mt-1">
|
||||
@@ -546,4 +557,3 @@ function initDragAndDrop(element, progressContainer, statusMessage, options = {}
|
||||
});
|
||||
}
|
||||
|
||||
|
||||
|
||||
+2
-317
File diff suppressed because one or more lines are too long
@@ -0,0 +1,12 @@
|
||||
/** @type {import('tailwindcss').Config} */
|
||||
module.exports = {
|
||||
content: [
|
||||
'./templates/**/*.html',
|
||||
'./static/js/**/*.js',
|
||||
],
|
||||
darkMode: 'class',
|
||||
theme: {
|
||||
extend: {},
|
||||
},
|
||||
plugins: [],
|
||||
}
|
||||
@@ -21,8 +21,6 @@
|
||||
<!-- Alpine.js moved to head for earlier loading -->
|
||||
<script src="https://cdn.jsdelivr.net/npm/alpinejs@3.x.x/dist/cdn.min.js" defer></script>
|
||||
{% block head_css %}
|
||||
<!-- Tailwind CSS and other CSS -->
|
||||
<link href="https://cdn.jsdelivr.net/npm/tailwindcss@2.2.19/dist/tailwind.min.css" rel="stylesheet">
|
||||
<!-- Font Awesome -->
|
||||
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.5.1/css/all.min.css"
|
||||
integrity="sha512-DTOQO9RWCH3ppGqcWaEA1BIZOC6xxalwEsw9c2QQeAIftl+Vegovlnee1c9QX4TctnWMn13TZye+giMm8e2LwA=="
|
||||
|
||||
@@ -1056,7 +1056,7 @@
|
||||
|
||||
html += `
|
||||
<div role="listitem">
|
||||
<a href="/files/${doc.file_id}" aria-label="${title} — ${scorePercent}% similarity (${scoreLabel})" style="text-decoration: none; color: inherit; display: block;">
|
||||
<a href="/files/${doc.file_id}/detail" aria-label="${title} — ${scorePercent}% similarity (${scoreLabel})" style="text-decoration: none; color: inherit; display: block;">
|
||||
<div style="display: flex; align-items: center; gap: 1rem; padding: 0.75rem 1rem; background-color: #f7fafc; border-radius: 0.5rem; border: 1px solid #e2e8f0; transition: border-color 0.2s; cursor: pointer;" onmouseover="this.style.borderColor='#4299e1'" onmouseout="this.style.borderColor='#e2e8f0'">
|
||||
<div style="flex-shrink: 0; width: 48px; height: 48px; border-radius: 50%; display: flex; align-items: center; justify-content: center; font-weight: 700; font-size: 0.875rem; color: white; background-color: ${scorePercent >= 80 ? '#48bb78' : scorePercent >= 50 ? '#ecc94b' : '#718096'};" aria-hidden="true">
|
||||
${scorePercent}%
|
||||
@@ -1091,20 +1091,19 @@
|
||||
}
|
||||
</script>
|
||||
{% endif %}
|
||||
|
||||
{% endblock %}
|
||||
|
||||
{% block content %}
|
||||
<div class="detail-container">
|
||||
<div style="display:flex;align-items:center;gap:1rem;margin-bottom:1.5rem;flex-wrap:wrap;">
|
||||
<a href="/files/{{ file.id }}" class="back-button" style="margin-bottom:0;" aria-label="Back to File Summary">
|
||||
<a href="/files" class="back-button" style="margin-bottom:0;" aria-label="Back to File List">
|
||||
<i class="fas fa-arrow-left" aria-hidden="true"></i>
|
||||
Back to File Summary
|
||||
Back to File List
|
||||
</a>
|
||||
{% if file %}
|
||||
<a href="/files/{{ file.id }}/detail" class="back-button" style="margin-bottom:0;" aria-label="View document detail for {{ file.original_filename }}">
|
||||
<a href="/files/{{ file.id }}" class="back-button" style="margin-bottom:0;" aria-label="View document for {{ file.original_filename }}">
|
||||
<i class="fas fa-eye" aria-hidden="true"></i>
|
||||
Document Detail
|
||||
View Document
|
||||
</a>
|
||||
{% endif %}
|
||||
</div>
|
||||
|
||||
@@ -1538,6 +1538,28 @@
|
||||
});
|
||||
}
|
||||
|
||||
function escapeHtml(str) {
|
||||
if (!str) return '';
|
||||
return String(str)
|
||||
.replace(/&/g, '&')
|
||||
.replace(/</g, '<')
|
||||
.replace(/>/g, '>')
|
||||
.replace(/"/g, '"')
|
||||
.replace(/'/g, ''');
|
||||
}
|
||||
|
||||
function sanitizeHighlight(html) {
|
||||
if (!html) return '';
|
||||
let safe = String(html)
|
||||
.replace(/<mark>/gi, '\x00MARK_OPEN\x00')
|
||||
.replace(/<\/mark>/gi, '\x00MARK_CLOSE\x00');
|
||||
safe = escapeHtml(safe);
|
||||
safe = safe
|
||||
.replace(/\x00MARK_OPEN\x00/g, '<mark>')
|
||||
.replace(/\x00MARK_CLOSE\x00/g, '</mark>');
|
||||
return safe;
|
||||
}
|
||||
|
||||
function renderSearchResults(data, q) {
|
||||
const panel = document.getElementById('search-results-panel');
|
||||
const list = document.getElementById('search-results-list');
|
||||
@@ -1555,25 +1577,31 @@
|
||||
|
||||
list.innerHTML = results.map(hit => {
|
||||
const fmt = hit._formatted || {};
|
||||
const title = fmt.document_title || hit.document_title || hit.original_filename || __i18n.untitled;
|
||||
const filename = fmt.original_filename || hit.original_filename || '';
|
||||
const snippet = fmt.ocr_text || '';
|
||||
const tags = Array.isArray(hit.tags) ? hit.tags.join(', ') : (hit.tags || '');
|
||||
const docType = hit.document_type || '';
|
||||
const titleRaw = fmt.document_title || hit.document_title || hit.original_filename || __i18n.untitled;
|
||||
const filenameRaw = fmt.original_filename || hit.original_filename || '';
|
||||
const snippetRaw = fmt.ocr_text || '';
|
||||
const tagsRaw = Array.isArray(hit.tags) ? hit.tags.join(', ') : (hit.tags || '');
|
||||
const docTypeRaw = hit.document_type || '';
|
||||
|
||||
const safeTitle = fmt.document_title ? sanitizeHighlight(titleRaw) : escapeHtml(titleRaw);
|
||||
const safeFilename = escapeHtml(filenameRaw);
|
||||
const safeSnippet = sanitizeHighlight(snippetRaw);
|
||||
const safeTags = escapeHtml(tagsRaw);
|
||||
const safeDocType = escapeHtml(docTypeRaw);
|
||||
|
||||
return `<div style="padding: 0.75rem 1rem; border-bottom: 1px solid #f3f4f6; display: flex; gap: 0.75rem; align-items: flex-start;">
|
||||
<div style="flex-shrink: 0; color: #3b82f6; font-size: 1.25rem; padding-top: 0.1rem;">
|
||||
<i class="fas fa-file-pdf"></i>
|
||||
</div>
|
||||
<div style="flex: 1; min-width: 0;">
|
||||
<div style="font-weight: 600; font-size: 0.9rem; color: #111827;">${title}</div>
|
||||
${filename ? `<div style="font-size: 0.8rem; color: #6b7280; margin-top: 0.15rem;">${filename}</div>` : ''}
|
||||
${docType ? `<span style="display: inline-block; margin-top: 0.25rem; padding: 0.1rem 0.5rem; background: #eff6ff; color: #1d4ed8; border-radius: 9999px; font-size: 0.75rem;">${docType}</span>` : ''}
|
||||
${tags ? `<span style="display: inline-block; margin-top: 0.25rem; margin-left: 0.25rem; padding: 0.1rem 0.5rem; background: #f0fdf4; color: #15803d; border-radius: 9999px; font-size: 0.75rem;">${tags}</span>` : ''}
|
||||
${snippet ? `<div style="margin-top: 0.4rem; font-size: 0.8rem; color: #374151; white-space: pre-wrap; word-break: break-word;">…${snippet}…</div>` : ''}
|
||||
<div style="font-weight: 600; font-size: 0.9rem; color: #111827;">${safeTitle}</div>
|
||||
${safeFilename ? `<div style="font-size: 0.8rem; color: #6b7280; margin-top: 0.15rem;">${safeFilename}</div>` : ''}
|
||||
${safeDocType ? `<span style="display: inline-block; margin-top: 0.25rem; padding: 0.1rem 0.5rem; background: #eff6ff; color: #1d4ed8; border-radius: 9999px; font-size: 0.75rem;">${safeDocType}</span>` : ''}
|
||||
${safeTags ? `<span style="display: inline-block; margin-top: 0.25rem; margin-left: 0.25rem; padding: 0.1rem 0.5rem; background: #f0fdf4; color: #15803d; border-radius: 9999px; font-size: 0.75rem;">${safeTags}</span>` : ''}
|
||||
${safeSnippet ? `<div style="margin-top: 0.4rem; font-size: 0.8rem; color: #374151; white-space: pre-wrap; word-break: break-word;">…${safeSnippet}…</div>` : ''}
|
||||
</div>
|
||||
<div style="flex-shrink: 0;">
|
||||
<a href="/files/${hit.file_id}" style="padding: 0.25rem 0.6rem; background: #f3f4f6; color: #374151; border-radius: 0.25rem; font-size: 0.8rem; text-decoration: none; white-space: nowrap;" title="${__i18n.viewFile}">
|
||||
<a href="/files/${escapeHtml(hit.file_id)}" style="padding: 0.25rem 0.6rem; background: #f3f4f6; color: #374151; border-radius: 0.25rem; font-size: 0.8rem; text-decoration: none; white-space: nowrap;" title="${__i18n.viewFile}">
|
||||
<i class="fas fa-external-link-alt"></i>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
@@ -1392,7 +1392,7 @@ function integrationsDashboard() {
|
||||
body: JSON.stringify({
|
||||
integration_type: intg.integration_type,
|
||||
config: intg.config,
|
||||
credentials: creds.credentials,
|
||||
credentials: creds,
|
||||
}),
|
||||
});
|
||||
const data = await resp.json();
|
||||
|
||||
@@ -298,9 +298,13 @@
|
||||
}
|
||||
|
||||
function escapeHtml(str) {
|
||||
const d = document.createElement('div');
|
||||
d.textContent = str;
|
||||
return d.innerHTML;
|
||||
if (str === null || str === undefined) return '';
|
||||
return String(str)
|
||||
.replace(/&/g, '&')
|
||||
.replace(/</g, '<')
|
||||
.replace(/>/g, '>')
|
||||
.replace(/"/g, '"')
|
||||
.replace(/'/g, ''');
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>DocuElevate - Create Account</title>
|
||||
<link href="https://cdn.jsdelivr.net/npm/tailwindcss@2.2.19/dist/tailwind.min.css" rel="stylesheet">
|
||||
<link rel="stylesheet" href="/static/styles.css" />
|
||||
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.5.1/css/all.min.css"
|
||||
integrity="sha512-DTOQO9RWCH3ppGqcWaEA1BIZOC6xxalwEsw9c2QQeAIftl+Vegovlnee1c9QX4TctnWMn13TZye+giMm8e2LwA=="
|
||||
crossorigin="anonymous" referrerpolicy="no-referrer" />
|
||||
|
||||
@@ -393,6 +393,16 @@ const i18nStrings = {
|
||||
configureNow: {{ _("status.configure_now") | tojson }},
|
||||
};
|
||||
|
||||
function escapeHtml(str) {
|
||||
if (!str) return '';
|
||||
return String(str)
|
||||
.replace(/&/g, '&')
|
||||
.replace(/</g, '<')
|
||||
.replace(/>/g, '>')
|
||||
.replace(/"/g, '"')
|
||||
.replace(/'/g, ''');
|
||||
}
|
||||
|
||||
document.addEventListener('DOMContentLoaded', function() {
|
||||
// Modal elements
|
||||
const resultModal = document.getElementById('resultModal');
|
||||
@@ -469,9 +479,8 @@ document.addEventListener('DOMContentLoaded', function() {
|
||||
const isSensitive = sensitiveKeys.some(sKey => key.toLowerCase().includes(sKey));
|
||||
|
||||
if (isSensitive && value !== 'Not set' && value !== '') {
|
||||
valueCell.textContent = value.slice(4) + '********' + value.slice(-4);
|
||||
// For better readability, we can also use HTML to mask the middle part of the string
|
||||
valueCell.innerHTML = value.slice(0, 4) + '<span class="text-gray-400">********</span>' + value.slice(-4);
|
||||
valueCell.innerHTML = escapeHtml(value.slice(0, 4)) + '<span class="text-gray-400">********</span>' + escapeHtml(value.slice(-4));
|
||||
} else {
|
||||
valueCell.textContent = value;
|
||||
}
|
||||
@@ -586,9 +595,9 @@ document.addEventListener('DOMContentLoaded', function() {
|
||||
if (data.status === 'success') {
|
||||
// If there's token info, we need to handle it specially
|
||||
if (data.token_info && data.token_info.expires_in_human) {
|
||||
let message = data.message || 'Connection successful';
|
||||
let message = escapeHtml(data.message || 'Connection successful');
|
||||
message += `<br><br><div class="bg-blue-50 p-3 rounded mt-2">
|
||||
<span class="font-medium">${i18nStrings.tokenValidFor}</span> ${data.token_info.expires_in_human}
|
||||
<span class="font-medium">${i18nStrings.tokenValidFor}</span> ${escapeHtml(data.token_info.expires_in_human)}
|
||||
</div>`;
|
||||
|
||||
modalTitle.textContent = i18nStrings.testSuccessful;
|
||||
@@ -647,12 +656,12 @@ document.addEventListener('DOMContentLoaded', function() {
|
||||
.then(data => {
|
||||
if (data.status === 'success') {
|
||||
// Create successful message
|
||||
let message = data.message || 'Connection successful';
|
||||
let message = escapeHtml(data.message || 'Connection successful');
|
||||
|
||||
// Add token expiration info if available (especially for Google Drive)
|
||||
if (data.token_info && data.token_info.expires_in_human) {
|
||||
message += `<br><br><div class="bg-blue-50 p-3 rounded mt-2">
|
||||
<span class="font-medium">${i18nStrings.tokenValidFor}</span> ${data.token_info.expires_in_human}
|
||||
<span class="font-medium">${i18nStrings.tokenValidFor}</span> ${escapeHtml(data.token_info.expires_in_human)}
|
||||
</div>`;
|
||||
|
||||
// Show the message with HTML
|
||||
|
||||
@@ -1,83 +0,0 @@
|
||||
{{- /*
|
||||
Celery Beat scheduler — publishes periodic tasks to the broker.
|
||||
Exactly ONE replica must run; never scale this deployment.
|
||||
*/ -}}
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: {{ include "docuelevate.fullname" . }}-beat
|
||||
namespace: {{ .Release.Namespace }}
|
||||
labels:
|
||||
{{- include "docuelevate.labels" . | nindent 4 }}
|
||||
app.kubernetes.io/component: beat
|
||||
spec:
|
||||
replicas: 1
|
||||
strategy:
|
||||
type: Recreate # Prevent two Beat instances from running simultaneously
|
||||
selector:
|
||||
matchLabels:
|
||||
{{- include "docuelevate.selectorLabels" . | nindent 6 }}
|
||||
app.kubernetes.io/component: beat
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
{{- include "docuelevate.selectorLabels" . | nindent 8 }}
|
||||
app.kubernetes.io/component: beat
|
||||
{{- with .Values.beat.podAnnotations }}
|
||||
annotations:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
spec:
|
||||
serviceAccountName: {{ include "docuelevate.serviceAccountName" . }}
|
||||
{{- with .Values.imagePullSecrets }}
|
||||
imagePullSecrets:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with .Values.beat.podSecurityContext }}
|
||||
securityContext:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
containers:
|
||||
- name: beat
|
||||
image: {{ include "docuelevate.image" . }}
|
||||
imagePullPolicy: {{ .Values.image.pullPolicy }}
|
||||
command:
|
||||
- celery
|
||||
- -A
|
||||
- app.celery_worker
|
||||
- beat
|
||||
- --loglevel=info
|
||||
envFrom:
|
||||
- configMapRef:
|
||||
name: {{ include "docuelevate.fullname" . }}-config
|
||||
- secretRef:
|
||||
name: {{ include "docuelevate.fullname" . }}-secret
|
||||
{{- with .Values.beat.securityContext }}
|
||||
securityContext:
|
||||
{{- toYaml . | nindent 12 }}
|
||||
{{- end }}
|
||||
resources:
|
||||
{{- toYaml .Values.beat.resources | nindent 12 }}
|
||||
volumeMounts:
|
||||
- name: workdir
|
||||
mountPath: /workdir
|
||||
volumes:
|
||||
- name: workdir
|
||||
{{- if .Values.workdir.persistence.enabled }}
|
||||
persistentVolumeClaim:
|
||||
claimName: {{ .Values.workdir.persistence.existingClaim | default (printf "%s-workdir" (include "docuelevate.fullname" .)) }}
|
||||
{{- else }}
|
||||
emptyDir: {}
|
||||
{{- end }}
|
||||
{{- with .Values.beat.nodeSelector }}
|
||||
nodeSelector:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with .Values.beat.affinity }}
|
||||
affinity:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with .Values.beat.tolerations }}
|
||||
tolerations:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
@@ -42,6 +42,7 @@ spec:
|
||||
- -A
|
||||
- app.celery_worker
|
||||
- worker
|
||||
- -B
|
||||
- --loglevel=info
|
||||
- -Q
|
||||
- document_processor,default,celery
|
||||
|
||||
@@ -121,10 +121,10 @@ api:
|
||||
type: ClusterIP
|
||||
port: 8000
|
||||
|
||||
# Liveness / readiness probes (unauthenticated endpoints for kubelet)
|
||||
# Liveness / readiness probes
|
||||
livenessProbe:
|
||||
httpGet:
|
||||
path: /api/diagnostic/healthz/live
|
||||
path: /api/health
|
||||
port: 8000
|
||||
initialDelaySeconds: 30
|
||||
periodSeconds: 20
|
||||
@@ -132,7 +132,7 @@ api:
|
||||
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /api/diagnostic/healthz/ready
|
||||
path: /api/health
|
||||
port: 8000
|
||||
initialDelaySeconds: 15
|
||||
periodSeconds: 10
|
||||
@@ -191,36 +191,7 @@ worker:
|
||||
drop: ["ALL"]
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Celery Beat scheduler (singleton — always exactly 1 replica)
|
||||
# Beat publishes periodic tasks; workers consume them from the broker.
|
||||
# ---------------------------------------------------------------------------
|
||||
beat:
|
||||
resources:
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 256Mi
|
||||
limits:
|
||||
cpu: 500m
|
||||
memory: 512Mi
|
||||
|
||||
podAnnotations: {}
|
||||
nodeSelector: {}
|
||||
tolerations: []
|
||||
affinity: {}
|
||||
|
||||
podSecurityContext:
|
||||
runAsNonRoot: true
|
||||
runAsUser: 1000
|
||||
fsGroup: 1000
|
||||
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
readOnlyRootFilesystem: false
|
||||
capabilities:
|
||||
drop: ["ALL"]
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Shared workdir volume (api + worker + beat mount the same PVC)
|
||||
# Shared workdir volume (api + worker mount the same PVC)
|
||||
# ---------------------------------------------------------------------------
|
||||
workdir:
|
||||
persistence:
|
||||
|
||||
+201
@@ -0,0 +1,201 @@
|
||||
"""
|
||||
Base setup for views, containing shared functionality and imports.
|
||||
"""
|
||||
|
||||
import logging
|
||||
from pathlib import Path
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, Request # noqa: F401
|
||||
from fastapi.templating import Jinja2Templates
|
||||
from sqlalchemy.orm import Session # noqa: F401
|
||||
|
||||
from app.auth import require_login # noqa: F401
|
||||
from app.config import settings
|
||||
from app.database import SessionLocal, get_db # noqa: F401
|
||||
from app.models import UserProfile
|
||||
from app.utils.i18n import (
|
||||
SUPPORTED_LANGUAGES,
|
||||
detect_language,
|
||||
format_date,
|
||||
format_datetime,
|
||||
format_number,
|
||||
get_suggested_languages,
|
||||
translate,
|
||||
)
|
||||
|
||||
# Set up Jinja2 templates
|
||||
templates_dir = Path(__file__).parent.parent.parent / "frontend" / "templates"
|
||||
templates = Jinja2Templates(directory=str(templates_dir))
|
||||
|
||||
# Add Python built-in functions to Jinja2 template globals
|
||||
templates.env.globals["min"] = min
|
||||
templates.env.globals["max"] = max
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# i18n Jinja2 integration
|
||||
# ---------------------------------------------------------------------------
|
||||
# The _() function is available in every template to translate UI strings.
|
||||
# Usage: {{ _("nav.dashboard") }} or {{ _("upload.max_size", size="10 MB") }}
|
||||
# The locale is automatically resolved from the request context.
|
||||
# A default English implementation is registered as a global so error handlers
|
||||
# that don't go through _inject_global_context still have the function available.
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
templates.env.globals["supported_languages"] = SUPPORTED_LANGUAGES
|
||||
templates.env.globals["_"] = lambda key, **kwargs: translate(key, "en", **kwargs)
|
||||
|
||||
# Customize Jinja2Templates to include app_version in all templates
|
||||
original_template_response = templates.TemplateResponse
|
||||
|
||||
|
||||
def _hydrate_language_from_db(request: Request, session_user: object) -> None:
|
||||
"""Load the user's preferred language from the DB into the session.
|
||||
|
||||
Called once per session when ``preferred_language`` is not yet in the
|
||||
session. A lightweight DB query fetches the stored preference so that
|
||||
:func:`detect_language` picks it up from the session on all subsequent
|
||||
requests without further DB access.
|
||||
"""
|
||||
from app.utils.i18n import SUPPORTED_LANGUAGE_CODES
|
||||
|
||||
user_id: str | None = None
|
||||
if isinstance(session_user, dict):
|
||||
user_id = (
|
||||
session_user.get("sub")
|
||||
or session_user.get("preferred_username")
|
||||
or session_user.get("email")
|
||||
or session_user.get("id")
|
||||
)
|
||||
elif isinstance(session_user, str):
|
||||
user_id = session_user
|
||||
|
||||
if not user_id:
|
||||
return
|
||||
|
||||
db = SessionLocal()
|
||||
try:
|
||||
profile = db.query(UserProfile).filter(UserProfile.user_id == user_id).first()
|
||||
if profile and profile.preferred_language and profile.preferred_language in SUPPORTED_LANGUAGE_CODES:
|
||||
request.session["preferred_language"] = profile.preferred_language
|
||||
except Exception: # noqa: BLE001 — intentionally broad; DB may be temporarily unavailable
|
||||
logger.debug("Could not hydrate language preference for user_id=%s", user_id)
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
|
||||
def _inject_global_context(ctx: dict) -> None:
|
||||
"""Inject shared global variables into every template context dict."""
|
||||
ctx.setdefault("version", settings.version)
|
||||
ctx.setdefault("release_name", getattr(settings, "release_name", None))
|
||||
ctx.setdefault("ui_default_color_scheme", getattr(settings, "ui_default_color_scheme", "system"))
|
||||
ctx.setdefault("multi_user_enabled", getattr(settings, "multi_user_enabled", False))
|
||||
ctx.setdefault("auth_enabled", getattr(settings, "auth_enabled", True))
|
||||
ctx.setdefault(
|
||||
"allow_signup",
|
||||
getattr(settings, "multi_user_enabled", False) and getattr(settings, "allow_local_signup", False),
|
||||
)
|
||||
ctx.setdefault("enable_factory_reset", getattr(settings, "enable_factory_reset", False))
|
||||
|
||||
# Sentry Browser SDK config (injected into every page so the JS SDK can initialise)
|
||||
# Normalize empty-string DSN to None so the {% if sentry_dsn %} template guard works correctly.
|
||||
_raw_dsn = getattr(settings, "sentry_dsn", None)
|
||||
ctx.setdefault("sentry_dsn", _raw_dsn if _raw_dsn else None)
|
||||
ctx.setdefault("sentry_environment", getattr(settings, "sentry_environment", "production"))
|
||||
ctx.setdefault("sentry_js_traces_sample_rate", getattr(settings, "sentry_js_traces_sample_rate", 0.0))
|
||||
ctx.setdefault(
|
||||
"sentry_js_replay_session_sample_rate",
|
||||
getattr(settings, "sentry_js_replay_session_sample_rate", 0.0),
|
||||
)
|
||||
ctx.setdefault(
|
||||
"sentry_js_replay_on_error_sample_rate",
|
||||
getattr(settings, "sentry_js_replay_on_error_sample_rate", 0.1),
|
||||
)
|
||||
|
||||
req = ctx.get("request")
|
||||
if req is not None:
|
||||
# CSRF token
|
||||
if hasattr(req, "state") and hasattr(req.state, "csrf_token"):
|
||||
ctx.setdefault("csrf_token", req.state.csrf_token)
|
||||
# Determine whether the current visitor is authenticated
|
||||
session_user = None
|
||||
if hasattr(req, "session"):
|
||||
session_user = req.session.get("user")
|
||||
# When auth is disabled every visitor is effectively "logged in"
|
||||
ctx.setdefault("is_logged_in", not getattr(settings, "auth_enabled", True) or session_user is not None)
|
||||
|
||||
# --- Hydrate session language from DB (once per session) ---
|
||||
# If the session doesn't have a preferred_language yet but the user
|
||||
# is logged in, load the stored preference from the database so that
|
||||
# detect_language() picks it up from the session on this and all
|
||||
# subsequent requests.
|
||||
if hasattr(req, "session") and "preferred_language" not in req.session and session_user is not None:
|
||||
_hydrate_language_from_db(req, session_user)
|
||||
|
||||
# --- i18n: detect language and register template helpers ---
|
||||
current_locale = detect_language(req)
|
||||
ctx.setdefault("current_locale", current_locale)
|
||||
|
||||
# Smart language suggestions for the compact nav-bar dropdown (5-7 languages)
|
||||
accept_header = req.headers.get("accept-language", "") if hasattr(req, "headers") else ""
|
||||
ctx.setdefault("suggested_languages", get_suggested_languages(current_locale, accept_header))
|
||||
|
||||
def _translate(key: str, **kwargs: object) -> str:
|
||||
return translate(key, current_locale, **kwargs)
|
||||
|
||||
def _format_date(value: object, short: bool = False) -> str:
|
||||
return format_date(value, current_locale, short=short) # type: ignore[arg-type]
|
||||
|
||||
def _format_datetime(value: object) -> str:
|
||||
return format_datetime(value, current_locale) # type: ignore[arg-type]
|
||||
|
||||
def _format_number(value: object) -> str:
|
||||
return format_number(value, current_locale) # type: ignore[arg-type]
|
||||
|
||||
ctx.setdefault("_", _translate)
|
||||
ctx.setdefault("format_date_l10n", _format_date)
|
||||
ctx.setdefault("format_datetime_l10n", _format_datetime)
|
||||
ctx.setdefault("format_number_l10n", _format_number)
|
||||
else:
|
||||
ctx.setdefault("is_logged_in", not getattr(settings, "auth_enabled", True))
|
||||
ctx.setdefault("current_locale", "en")
|
||||
ctx.setdefault("_", lambda key, **kw: translate(key, "en", **kw))
|
||||
|
||||
|
||||
def template_response_with_version(*args, **kwargs):
|
||||
"""Wrapper for TemplateResponse to include version and CSRF token in all templates.
|
||||
|
||||
Handles both old-style and new-style Starlette TemplateResponse calls:
|
||||
- Old-style (Starlette <1.0): TemplateResponse(name, {"request": req, ...}, ...)
|
||||
- New-style (Starlette 1.0+): TemplateResponse(request, name, context={...}, ...)
|
||||
"""
|
||||
if len(args) >= 1 and isinstance(args[0], str):
|
||||
# Old-style call: first positional arg is the template name (string).
|
||||
# Convert to new-style: (request, name, context=..., ...)
|
||||
name = args[0]
|
||||
if len(args) >= 2 and isinstance(args[1], dict):
|
||||
context = args[1]
|
||||
# Old-style may have status_code as 3rd positional arg
|
||||
if len(args) >= 3 and "status_code" not in kwargs:
|
||||
kwargs["status_code"] = args[2]
|
||||
else:
|
||||
context = kwargs.pop("context", {})
|
||||
request_obj = context.pop("request", None)
|
||||
if request_obj is not None:
|
||||
context["request"] = request_obj
|
||||
_inject_global_context(context)
|
||||
if request_obj is not None:
|
||||
return original_template_response(request_obj, name, context=context, **kwargs)
|
||||
return original_template_response(name, context=context, **kwargs)
|
||||
|
||||
# New-style call: (request, name, context=..., ...)
|
||||
if "context" in kwargs and isinstance(kwargs["context"], dict):
|
||||
_inject_global_context(kwargs["context"])
|
||||
elif len(args) >= 3 and isinstance(args[2], dict):
|
||||
_inject_global_context(args[2])
|
||||
return original_template_response(*args, **kwargs)
|
||||
|
||||
|
||||
templates.TemplateResponse = template_response_with_version
|
||||
|
||||
# Set up logging
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -55,6 +55,7 @@ nav:
|
||||
- Google Drive: GoogleDriveSetup
|
||||
- OneDrive: OneDriveSetup
|
||||
- Amazon S3: AmazonS3Setup
|
||||
- Evernote: EvernoteSetup
|
||||
- Authentication: AuthenticationSetup
|
||||
- Notifications: NotificationsSetup
|
||||
- Security:
|
||||
|
||||
Generated
+346
-335
File diff suppressed because it is too large
Load Diff
@@ -58,6 +58,13 @@
|
||||
"eslint-config-expo": "~10.0.0",
|
||||
"typescript": "^5.3.0"
|
||||
},
|
||||
"overrides": {
|
||||
"postcss": "8.5.15",
|
||||
"uuid": "11.1.1",
|
||||
"brace-expansion@^1.1.7": "1.1.13",
|
||||
"brace-expansion@^2.0.2": "2.1.0",
|
||||
"brace-expansion@^5.0.2": "5.0.6"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=20.19.4"
|
||||
},
|
||||
|
||||
+1
-1
@@ -1,5 +1,5 @@
|
||||
[build-system]
|
||||
requires = ["setuptools>=45", "wheel"]
|
||||
requires = ["setuptools>=82.0.1", "wheel"]
|
||||
build-backend = "setuptools.build_meta"
|
||||
|
||||
[project]
|
||||
|
||||
@@ -0,0 +1,34 @@
|
||||
import sys
|
||||
from unittest.mock import MagicMock
|
||||
from fastapi.templating import Jinja2Templates
|
||||
|
||||
import os
|
||||
# We don't really need a real path, but let's mock it
|
||||
os.makedirs("templates", exist_ok=True)
|
||||
with open("templates/files.html", "w") as f:
|
||||
f.write("Hello")
|
||||
|
||||
templates = Jinja2Templates(directory="templates")
|
||||
original_template_response = templates.TemplateResponse
|
||||
|
||||
def template_response_with_version(*args, **kwargs):
|
||||
if len(args) == 2 and isinstance(args[0], str) and isinstance(args[1], dict):
|
||||
context = args[1]
|
||||
request = context.get("request")
|
||||
if request is not None:
|
||||
# THIS IS MY FIX
|
||||
print("Running fix logic")
|
||||
return original_template_response(request=request, name=args[0], context=context, **kwargs)
|
||||
|
||||
print("Running original fallback logic")
|
||||
return original_template_response(*args, **kwargs)
|
||||
|
||||
templates.TemplateResponse = template_response_with_version
|
||||
|
||||
req = MagicMock()
|
||||
try:
|
||||
templates.TemplateResponse("files.html", {"request": req})
|
||||
print("SUCCESS")
|
||||
except Exception as e:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
@@ -0,0 +1,33 @@
|
||||
import sys
|
||||
from unittest.mock import MagicMock
|
||||
from fastapi.templating import Jinja2Templates
|
||||
|
||||
import os
|
||||
os.makedirs("templates", exist_ok=True)
|
||||
with open("templates/files.html", "w") as f:
|
||||
f.write("Hello")
|
||||
|
||||
templates = Jinja2Templates(directory="templates")
|
||||
original_template_response = templates.TemplateResponse
|
||||
|
||||
def template_response_with_version(*args, **kwargs):
|
||||
if len(args) == 2 and isinstance(args[0], str) and isinstance(args[1], dict):
|
||||
context = args[1]
|
||||
request = context.get("request")
|
||||
if request is not None:
|
||||
# THIS IS MY FIX
|
||||
print("Running fix logic")
|
||||
return original_template_response(request=request, name=args[0], context=context, **kwargs)
|
||||
|
||||
print("Running original fallback logic", args, kwargs)
|
||||
return original_template_response(*args, **kwargs)
|
||||
|
||||
templates.TemplateResponse = template_response_with_version
|
||||
|
||||
req = MagicMock()
|
||||
try:
|
||||
templates.TemplateResponse(request=req, name="files.html", context={"request": req})
|
||||
print("SUCCESS")
|
||||
except Exception as e:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
@@ -0,0 +1,33 @@
|
||||
import sys
|
||||
from unittest.mock import MagicMock
|
||||
from fastapi.templating import Jinja2Templates
|
||||
|
||||
import os
|
||||
os.makedirs("templates", exist_ok=True)
|
||||
with open("templates/files.html", "w") as f:
|
||||
f.write("Hello")
|
||||
|
||||
templates = Jinja2Templates(directory="templates")
|
||||
original_template_response = templates.TemplateResponse
|
||||
|
||||
def template_response_with_version(*args, **kwargs):
|
||||
if len(args) == 2 and isinstance(args[0], str) and isinstance(args[1], dict):
|
||||
context = args[1]
|
||||
request = context.get("request")
|
||||
if request is not None:
|
||||
# THIS IS MY FIX
|
||||
print("Running fix logic")
|
||||
return original_template_response(request=request, name=args[0], context=context, **kwargs)
|
||||
|
||||
print("Running original fallback logic", args, kwargs)
|
||||
return original_template_response(*args, **kwargs)
|
||||
|
||||
templates.TemplateResponse = template_response_with_version
|
||||
|
||||
req = MagicMock()
|
||||
try:
|
||||
templates.TemplateResponse("files.html", {"request": req}, status_code=200)
|
||||
print("SUCCESS")
|
||||
except Exception as e:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
@@ -0,0 +1,35 @@
|
||||
import sys
|
||||
from unittest.mock import MagicMock
|
||||
from fastapi.templating import Jinja2Templates
|
||||
|
||||
import os
|
||||
os.makedirs("templates", exist_ok=True)
|
||||
with open("templates/files.html", "w") as f:
|
||||
f.write("Hello")
|
||||
|
||||
templates = Jinja2Templates(directory="templates")
|
||||
original_template_response = templates.TemplateResponse
|
||||
|
||||
def template_response_with_version(*args, **kwargs):
|
||||
print("ARGS:", args)
|
||||
print("KWARGS:", kwargs)
|
||||
if len(args) == 2 and isinstance(args[0], str) and isinstance(args[1], dict):
|
||||
context = args[1]
|
||||
request = context.get("request")
|
||||
if request is not None:
|
||||
# THIS IS MY FIX
|
||||
print("Running fix logic")
|
||||
return original_template_response(request=request, name=args[0], context=context, **kwargs)
|
||||
|
||||
print("Running original fallback logic", args, kwargs)
|
||||
return original_template_response(*args, **kwargs)
|
||||
|
||||
templates.TemplateResponse = template_response_with_version
|
||||
|
||||
req = MagicMock()
|
||||
try:
|
||||
templates.TemplateResponse("files.html", context={"request": req})
|
||||
print("SUCCESS")
|
||||
except Exception as e:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
@@ -4,14 +4,14 @@
|
||||
# Testing
|
||||
pytest>=8.0.0
|
||||
pytest-cov>=4.1.0
|
||||
pytest-asyncio>=0.23.0
|
||||
pytest-asyncio>=1.4.0
|
||||
pytest-mock>=3.12.0
|
||||
pytest-timeout>=2.3.0 # Per-test timeout enforcement to prevent CI hangs
|
||||
httpx>=0.26.0 # For async test client
|
||||
testcontainers>=3.7.1 # For integration tests with real containers
|
||||
fpdf2>=2.8.0 # For generating test PDF documents in integration tests
|
||||
minio>=7.1.0 # For MinIO/S3 integration tests
|
||||
redis>=4.5.0 # For Redis integration tests
|
||||
redis>=8.0.0 # For Redis integration tests
|
||||
boto3>=1.26.0 # For S3 integration tests
|
||||
|
||||
# Code quality
|
||||
@@ -34,7 +34,7 @@ pip-audit>=2.7.0 # Dependency vulnerability scanning against OSV/PyPA advisory
|
||||
pre-commit>=3.6.0
|
||||
|
||||
# License compliance
|
||||
pip-licenses==5.5.1 # For license compliance checking
|
||||
pip-licenses==5.5.5 # For license compliance checking
|
||||
|
||||
# Release automation
|
||||
python-semantic-release>=9.0.0
|
||||
|
||||
+7
-3
@@ -2,8 +2,9 @@ fastapi[all] # Web framework with all extras
|
||||
uvicorn # ASGI server
|
||||
celery # Task queue
|
||||
redis # Message broker for Celery
|
||||
sqlalchemy # Database ORM
|
||||
pydantic # Data validation
|
||||
sqlalchemy # Database ORM
|
||||
psycopg[binary]>=3.2,<4.0 # PostgreSQL driver for HA database deployments
|
||||
pydantic # Data validation
|
||||
cryptography>=41.0.0 # Encryption for sensitive settings in database
|
||||
openai # GPT integration for metadata extraction
|
||||
pypdf>=3.9.0 # PDF processing for text extraction, metadata editing and rotation (upgraded from PyPDF2 to fix CVE-2023-36464)
|
||||
@@ -37,6 +38,9 @@ paramiko>=3.4.0 # SSH/SFTP implementation for Python (LGPL license)
|
||||
# iCloud Drive
|
||||
pyicloud>=2.4.0 # Unofficial Apple iCloud API client (MIT license)
|
||||
|
||||
# Evernote
|
||||
evernote3>=1.25.14 # Evernote Cloud API SDK for Python 3 (BSD license)
|
||||
|
||||
# Safe XML parsing (protection against XML bomb / XXE attacks)
|
||||
defusedxml>=0.7.1
|
||||
|
||||
@@ -51,7 +55,7 @@ pytesseract>=0.3.10 # Python wrapper for Tesseract OCR
|
||||
pdf2image>=1.17.0 # Convert PDF pages to images (used by Tesseract and EasyOCR providers)
|
||||
ocrmypdf>=16.0.0,<18.0.0 # Post-processing: embeds searchable text layers into PDFs via Tesseract
|
||||
meilisearch>=0.31.0 # Full-text search engine client
|
||||
stripe>=7.0.0,<15.0.0 # Stripe billing SDK (MIT license)
|
||||
stripe>=7.0.0,<16.0.0 # Stripe billing SDK (MIT license)
|
||||
|
||||
# Error and performance monitoring
|
||||
sentry-sdk[fastapi,celery,sqlalchemy]>=2.20.0,<3.0.0
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
Hello
|
||||
@@ -83,8 +83,6 @@ class TestGotenbergCoverageDocuments:
|
||||
".tif",
|
||||
".webp",
|
||||
".svg",
|
||||
".heic",
|
||||
".heif",
|
||||
}
|
||||
_html_extensions = {".html", ".htm"}
|
||||
_markdown_extensions = {".md", ".markdown"}
|
||||
|
||||
@@ -267,6 +267,15 @@ class TestTestDropboxToken:
|
||||
class TestSaveDropboxSettings:
|
||||
"""Tests for save_dropbox_settings endpoint."""
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def _admin_override(self):
|
||||
from app.api.dropbox import _require_admin
|
||||
from app.main import app as fastapi_app
|
||||
|
||||
fastapi_app.dependency_overrides[_require_admin] = lambda: {"is_admin": True}
|
||||
yield
|
||||
fastapi_app.dependency_overrides.pop(_require_admin, None)
|
||||
|
||||
@patch("app.api.dropbox.settings")
|
||||
def test_save_settings_env_not_found(self, mock_settings, client):
|
||||
"""Test that missing .env file is non-fatal — DB write still succeeds."""
|
||||
|
||||
@@ -360,6 +360,15 @@ class TestFormatTimeRemaining:
|
||||
class TestSaveGoogleDriveSettings:
|
||||
"""Tests for POST /google-drive/save-settings endpoint."""
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def _admin_override(self):
|
||||
from app.api.google_drive import _require_admin
|
||||
from app.main import app as fastapi_app
|
||||
|
||||
fastapi_app.dependency_overrides[_require_admin] = lambda: {"is_admin": True}
|
||||
yield
|
||||
fastapi_app.dependency_overrides.pop(_require_admin, None)
|
||||
|
||||
@patch("builtins.open", new_callable=mock_open, read_data="# Existing config\n")
|
||||
@patch("os.path.exists")
|
||||
@patch("os.path.dirname")
|
||||
@@ -481,18 +490,17 @@ class TestSaveGoogleDriveSettings:
|
||||
|
||||
assert response.status_code == 200
|
||||
|
||||
@patch("os.path.exists")
|
||||
@patch("os.path.dirname")
|
||||
@patch("app.api.google_drive.os")
|
||||
@patch("app.config.settings")
|
||||
def test_save_settings_exception_handling(self, mock_settings, mock_dirname, mock_exists, client: TestClient):
|
||||
"""Test exception handling in save settings."""
|
||||
mock_exists.side_effect = Exception("Unexpected error")
|
||||
def test_save_settings_exception_handling(self, mock_settings, mock_os, client: TestClient):
|
||||
"""Test that exceptions in .env write are non-fatal — DB write still succeeds."""
|
||||
mock_os.path.exists.side_effect = Exception("Unexpected error")
|
||||
|
||||
response = client.post("/api/google-drive/save-settings", data={"refresh_token": "token", "use_oauth": "true"})
|
||||
|
||||
assert response.status_code == 500
|
||||
data = response.json()
|
||||
assert "failed to save" in data["detail"].lower()
|
||||
# .env write exception is caught; endpoint succeeds via DB write
|
||||
assert response.status_code == 200
|
||||
assert response.json()["status"] == "success"
|
||||
|
||||
|
||||
@pytest.mark.unit
|
||||
|
||||
@@ -195,6 +195,15 @@ class TestGetGoogleDriveTokenInfo:
|
||||
class TestSaveGoogleDriveSettings:
|
||||
"""Test save_google_drive_settings endpoint edge cases."""
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def _admin_override(self):
|
||||
from app.api.google_drive import _require_admin
|
||||
from app.main import app as fastapi_app
|
||||
|
||||
fastapi_app.dependency_overrides[_require_admin] = lambda: {"is_admin": True}
|
||||
yield
|
||||
fastapi_app.dependency_overrides.pop(_require_admin, None)
|
||||
|
||||
@patch("app.api.google_drive.settings")
|
||||
@patch("os.path.exists")
|
||||
def test_save_settings_env_file_not_exists(self, mock_exists, mock_settings, client: TestClient):
|
||||
|
||||
@@ -152,11 +152,16 @@ class TestGetTokenInfoCredentialsBranches:
|
||||
|
||||
@pytest.mark.unit
|
||||
class TestSaveGoogleDriveSettingsFalsyFields:
|
||||
"""Cover branches 395->397, 449->451, 468->470 in save_google_drive_settings.
|
||||
"""Cover branches 395->397, 449->451, 468->470 in save_google_drive_settings."""
|
||||
|
||||
Note: the Google Drive save endpoint is named save_google_drive_settings in the
|
||||
source (app/api/google_drive.py).
|
||||
"""
|
||||
@pytest.fixture(autouse=True)
|
||||
def _admin_override(self):
|
||||
from app.api.google_drive import _require_admin
|
||||
from app.main import app as fastapi_app
|
||||
|
||||
fastapi_app.dependency_overrides[_require_admin] = lambda: {"is_admin": True}
|
||||
yield
|
||||
fastapi_app.dependency_overrides.pop(_require_admin, None)
|
||||
|
||||
@patch("app.api.google_drive.settings")
|
||||
@patch("os.path.exists", return_value=False)
|
||||
@@ -177,6 +182,7 @@ class TestSaveGoogleDriveSettingsFalsyFields:
|
||||
with patch("app.api.google_drive.notify_settings_updated"):
|
||||
result = await save_google_drive_settings(
|
||||
request=mock_request,
|
||||
_admin={"is_admin": True},
|
||||
refresh_token="", # falsy → branches 395->397 and 449->451
|
||||
client_id="cid",
|
||||
client_secret=None,
|
||||
|
||||
@@ -524,7 +524,10 @@ class TestTestImapConnection:
|
||||
from app.api.imap_accounts import _test_imap_connection
|
||||
|
||||
mock_mail = MagicMock()
|
||||
with patch("imaplib.IMAP4_SSL", return_value=mock_mail):
|
||||
with (
|
||||
patch("app.api.imap_accounts.is_private_ip", return_value=False),
|
||||
patch("imaplib.IMAP4_SSL", return_value=mock_mail),
|
||||
):
|
||||
result = _test_imap_connection(
|
||||
"imap.example.com",
|
||||
993,
|
||||
@@ -541,7 +544,10 @@ class TestTestImapConnection:
|
||||
"""An exception raised by IMAP4_SSL returns success=False."""
|
||||
from app.api.imap_accounts import _test_imap_connection
|
||||
|
||||
with patch("imaplib.IMAP4_SSL", side_effect=Exception("auth failed")):
|
||||
with (
|
||||
patch("app.api.imap_accounts.is_private_ip", return_value=False),
|
||||
patch("imaplib.IMAP4_SSL", side_effect=Exception("auth failed")),
|
||||
):
|
||||
result = _test_imap_connection(
|
||||
"imap.example.com",
|
||||
993,
|
||||
@@ -557,7 +563,10 @@ class TestTestImapConnection:
|
||||
"""An OSError returns success=False with a network error message."""
|
||||
from app.api.imap_accounts import _test_imap_connection
|
||||
|
||||
with patch("imaplib.IMAP4", side_effect=OSError("connection refused")):
|
||||
with (
|
||||
patch("app.api.imap_accounts.is_private_ip", return_value=False),
|
||||
patch("imaplib.IMAP4", side_effect=OSError("connection refused")),
|
||||
):
|
||||
result = _test_imap_connection(
|
||||
"bad-host",
|
||||
143,
|
||||
|
||||
@@ -998,6 +998,23 @@ class TestConnectionTestEndpoint:
|
||||
assert data["success"] is False
|
||||
assert "Missing" in data["message"]
|
||||
|
||||
def test_test_imap_blocks_private_ip(self, int_client):
|
||||
"""IMAP test with private IP returns failure (SSRF protection)."""
|
||||
payload = {
|
||||
"integration_type": "IMAP",
|
||||
"config": {
|
||||
"host": "127.0.0.1",
|
||||
"port": 993,
|
||||
"username": "user",
|
||||
},
|
||||
"credentials": {"password": "pass"},
|
||||
}
|
||||
resp = int_client.post("/api/integrations/test", json=payload)
|
||||
assert resp.status_code == 200
|
||||
data = resp.json()
|
||||
assert data["success"] is False
|
||||
assert "Invalid hostname or IP address" in data["message"]
|
||||
|
||||
def test_test_s3_missing_bucket(self, int_client):
|
||||
"""S3 test with missing bucket returns failure."""
|
||||
payload = {
|
||||
@@ -1011,6 +1028,19 @@ class TestConnectionTestEndpoint:
|
||||
assert data["success"] is False
|
||||
assert "bucket" in data["message"].lower()
|
||||
|
||||
def test_test_s3_blocks_private_ip(self, int_client):
|
||||
"""S3 test with private IP endpoint returns failure (SSRF protection)."""
|
||||
payload = {
|
||||
"integration_type": "S3",
|
||||
"config": {"bucket": "my-bucket", "endpoint_url": "http://127.0.0.1:9000"},
|
||||
"credentials": {"access_key_id": "AKIA", "secret_access_key": "secret"},
|
||||
}
|
||||
resp = int_client.post("/api/integrations/test", json=payload)
|
||||
assert resp.status_code == 200
|
||||
data = resp.json()
|
||||
assert data["success"] is False
|
||||
assert "Invalid endpoint URL or private IP" in data["message"]
|
||||
|
||||
def test_test_webdav_missing_url(self, int_client):
|
||||
"""WebDAV test with missing URL returns failure."""
|
||||
payload = {
|
||||
|
||||
@@ -342,6 +342,15 @@ class TestFormatTimeRemaining:
|
||||
class TestSaveOneDriveSettings:
|
||||
"""Tests for POST /onedrive/save-settings endpoint."""
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def _admin_override(self):
|
||||
from app.api.onedrive import _require_admin
|
||||
from app.main import app as fastapi_app
|
||||
|
||||
fastapi_app.dependency_overrides[_require_admin] = lambda: {"is_admin": True}
|
||||
yield
|
||||
fastapi_app.dependency_overrides.pop(_require_admin, None)
|
||||
|
||||
@patch("builtins.open", new_callable=mock_open, read_data="# Existing config\n")
|
||||
@patch("os.path.exists")
|
||||
@patch("os.path.dirname")
|
||||
|
||||
@@ -294,6 +294,15 @@ class TestTokenRotationEnvAppendLine:
|
||||
class TestSaveSettingsException:
|
||||
"""Cover lines 324-326: save_onedrive_settings outer exception handler."""
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def _admin_override(self):
|
||||
from app.api.onedrive import _require_admin
|
||||
from app.main import app as fastapi_app
|
||||
|
||||
fastapi_app.dependency_overrides[_require_admin] = lambda: {"is_admin": True}
|
||||
yield
|
||||
fastapi_app.dependency_overrides.pop(_require_admin, None)
|
||||
|
||||
def test_save_settings_outer_exception(self, client: TestClient):
|
||||
"""Trigger the outer exception handler in save_onedrive_settings."""
|
||||
with patch("app.api.onedrive.notify_settings_updated", side_effect=Exception("Unexpected boom")):
|
||||
|
||||
@@ -47,6 +47,27 @@ class TestProcessEndpoints:
|
||||
data = response.json()
|
||||
assert data["task_id"] == "test-task-id"
|
||||
assert data["status"] == "queued"
|
||||
mock_task.delay.assert_called_once_with(str(test_file))
|
||||
|
||||
def test_send_to_dropbox_endpoint_file_not_found(self, client):
|
||||
"""Test POST /api/send_to_dropbox/ directly mapping to endpoint name with non-existent file."""
|
||||
response = client.post("/api/send_to_dropbox/?file_path=nonexistent_endpoint.pdf")
|
||||
assert response.status_code == 400
|
||||
|
||||
def test_send_to_dropbox_endpoint_success(self, client, tmp_path):
|
||||
"""Test POST /api/send_to_dropbox/ directly mapping to endpoint name with existing file."""
|
||||
test_file = tmp_path / "processed" / "test_endpoint.pdf"
|
||||
test_file.parent.mkdir(parents=True)
|
||||
test_file.write_text("test content endpoint")
|
||||
|
||||
with patch("app.api.process.upload_to_dropbox") as mock_task:
|
||||
mock_task.delay.return_value = Mock(id="test-task-id-endpoint")
|
||||
response = client.post(f"/api/send_to_dropbox/?file_path={test_file}")
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
assert data["task_id"] == "test-task-id-endpoint"
|
||||
assert data["status"] == "queued"
|
||||
mock_task.delay.assert_called_once_with(str(test_file))
|
||||
|
||||
def test_send_to_paperless_file_not_found(self, client):
|
||||
"""Test POST /api/send_to_paperless/ with non-existent file."""
|
||||
|
||||
+337
-160
@@ -1,191 +1,368 @@
|
||||
"""Tests for the saved searches API (app/api/saved_searches.py)."""
|
||||
|
||||
import pytest
|
||||
from fastapi.testclient import TestClient
|
||||
from sqlalchemy import create_engine
|
||||
from sqlalchemy.orm import sessionmaker
|
||||
from sqlalchemy.pool import StaticPool
|
||||
|
||||
from app.database import Base, get_db
|
||||
from app.models import SavedSearch
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Test data constants
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
_OWNER = "test_user@example.com"
|
||||
_OTHER_OWNER = "other_user@example.com"
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Shared fixture helpers
|
||||
# Saved searches CRUD tests
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def int_engine():
|
||||
"""In-memory SQLite engine for integration tests."""
|
||||
engine = create_engine(
|
||||
"sqlite:///:memory:",
|
||||
connect_args={"check_same_thread": False},
|
||||
poolclass=StaticPool,
|
||||
)
|
||||
Base.metadata.create_all(bind=engine)
|
||||
yield engine
|
||||
Base.metadata.drop_all(bind=engine)
|
||||
@pytest.mark.unit
|
||||
class TestSavedSearchesCRUD:
|
||||
"""Tests for saved searches CRUD API endpoints."""
|
||||
|
||||
def test_list_saved_searches_empty(self, client: TestClient):
|
||||
"""GET /api/saved-searches returns empty list when no searches exist."""
|
||||
response = client.get("/api/saved-searches")
|
||||
assert response.status_code == 200
|
||||
assert response.json() == []
|
||||
|
||||
@pytest.fixture()
|
||||
def int_session(int_engine):
|
||||
"""DB session scoped to one test."""
|
||||
Session = sessionmaker(bind=int_engine)
|
||||
session = Session()
|
||||
yield session
|
||||
session.close()
|
||||
|
||||
|
||||
def _make_client(int_engine, owner_id: str = _OWNER):
|
||||
"""Return a TestClient with *owner_id* injected as the authenticated user."""
|
||||
from unittest.mock import patch
|
||||
|
||||
from app.main import app
|
||||
|
||||
def override_db():
|
||||
Session = sessionmaker(bind=int_engine)
|
||||
session = Session()
|
||||
try:
|
||||
yield session
|
||||
finally:
|
||||
session.close()
|
||||
|
||||
app.dependency_overrides[get_db] = override_db
|
||||
with patch("app.api.saved_searches._get_user_id", return_value=owner_id):
|
||||
with TestClient(app, base_url="http://localhost", raise_server_exceptions=False) as client:
|
||||
yield client
|
||||
app.dependency_overrides.clear()
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def int_client(int_engine):
|
||||
"""TestClient authenticated as _OWNER."""
|
||||
yield from _make_client(int_engine, _OWNER)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# CRUD tests
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.integration
|
||||
class TestSavedSearchesAPI:
|
||||
"""Tests for Saved Searches endpoints."""
|
||||
|
||||
def test_list_saved_searches_empty(self, int_client):
|
||||
"""No saved searches returns empty list."""
|
||||
resp = int_client.get("/api/saved-searches")
|
||||
assert resp.status_code == 200
|
||||
assert resp.json() == []
|
||||
|
||||
def test_create_saved_search(self, int_client):
|
||||
"""Create a saved search and verify the response."""
|
||||
payload = {"name": "My Invoices", "filters": {"tags": "invoice", "document_type": "Invoice"}}
|
||||
resp = int_client.post("/api/saved-searches", json=payload)
|
||||
assert resp.status_code == 201
|
||||
data = resp.json()
|
||||
def test_create_saved_search(self, client: TestClient):
|
||||
"""POST /api/saved-searches creates a new saved search."""
|
||||
payload = {
|
||||
"name": "My Invoices",
|
||||
"filters": {"tags": "invoice", "status": "completed"},
|
||||
}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
assert response.status_code == 201
|
||||
data = response.json()
|
||||
assert data["name"] == "My Invoices"
|
||||
assert data["filters"] == {"tags": "invoice", "document_type": "Invoice"}
|
||||
assert data["filters"]["tags"] == "invoice"
|
||||
assert data["filters"]["status"] == "completed"
|
||||
assert "id" in data
|
||||
|
||||
def test_create_saved_search_invalid_filters(self, int_client):
|
||||
"""Creating with invalid filters returns 422."""
|
||||
# Missing filters parameter (or empty after sanitization)
|
||||
payload = {"name": "My Invoices", "filters": {}}
|
||||
resp = int_client.post("/api/saved-searches", json=payload)
|
||||
assert resp.status_code == 422
|
||||
def test_create_and_list_saved_search(self, client: TestClient):
|
||||
"""Creating a saved search makes it appear in the list."""
|
||||
payload = {
|
||||
"name": "PDF Files",
|
||||
"filters": {"mime_type": "application/pdf"},
|
||||
}
|
||||
client.post("/api/saved-searches", json=payload)
|
||||
|
||||
# Invalid filters format
|
||||
payload2 = {"name": "My Invoices", "filters": "not_a_dict"}
|
||||
resp2 = int_client.post("/api/saved-searches", json=payload2)
|
||||
assert resp2.status_code == 422
|
||||
response = client.get("/api/saved-searches")
|
||||
assert response.status_code == 200
|
||||
searches = response.json()
|
||||
assert len(searches) == 1
|
||||
assert searches[0]["name"] == "PDF Files"
|
||||
|
||||
def test_create_saved_search_duplicate(self, int_client):
|
||||
"""Creating a duplicate named search returns 409."""
|
||||
payload = {"name": "Duplicate", "filters": {"q": "test"}}
|
||||
int_client.post("/api/saved-searches", json=payload)
|
||||
resp = int_client.post("/api/saved-searches", json=payload)
|
||||
assert resp.status_code == 409
|
||||
def test_create_saved_search_missing_name(self, client: TestClient):
|
||||
"""POST /api/saved-searches without name returns 422."""
|
||||
payload = {"filters": {"status": "completed"}}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
assert response.status_code == 422
|
||||
|
||||
def test_create_saved_search_limit(self, int_client, int_session):
|
||||
"""Exceeding MAX_SAVED_SEARCHES_PER_USER returns 409."""
|
||||
# Create 50 searches using the API to ensure they are visible
|
||||
for i in range(50):
|
||||
resp = int_client.post("/api/saved-searches", json={"name": f"Search LIMIT {i}", "filters": {"q": "test"}})
|
||||
assert resp.status_code == 201
|
||||
def test_create_saved_search_empty_filters(self, client: TestClient):
|
||||
"""POST /api/saved-searches with empty filters returns 422."""
|
||||
payload = {"name": "Empty", "filters": {}}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
assert response.status_code == 422
|
||||
|
||||
payload = {"name": "One too many", "filters": {"q": "test"}}
|
||||
resp = int_client.post("/api/saved-searches", json=payload)
|
||||
assert resp.status_code == 409
|
||||
def test_create_saved_search_invalid_filter_keys(self, client: TestClient):
|
||||
"""POST /api/saved-searches ignores unknown filter keys."""
|
||||
payload = {
|
||||
"name": "With unknown keys",
|
||||
"filters": {"invalid_key": "value", "status": "completed"},
|
||||
}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
assert response.status_code == 201
|
||||
data = response.json()
|
||||
# Only valid filter key should remain
|
||||
assert "invalid_key" not in data["filters"]
|
||||
assert data["filters"]["status"] == "completed"
|
||||
|
||||
def test_update_saved_search(self, int_client):
|
||||
"""Update an existing saved search."""
|
||||
payload = {"name": "Original Name", "filters": {"q": "test"}}
|
||||
created = int_client.post("/api/saved-searches", json=payload).json()
|
||||
search_id = created["id"]
|
||||
def test_create_saved_search_only_invalid_keys(self, client: TestClient):
|
||||
"""POST with only invalid filter keys returns 422."""
|
||||
payload = {
|
||||
"name": "All invalid",
|
||||
"filters": {"bad_key": "value"},
|
||||
}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
assert response.status_code == 422
|
||||
|
||||
update_payload = {"name": "Updated Name", "filters": {"tags": "new"}}
|
||||
resp = int_client.put(f"/api/saved-searches/{search_id}", json=update_payload)
|
||||
assert resp.status_code == 200
|
||||
data = resp.json()
|
||||
assert data["name"] == "Updated Name"
|
||||
assert data["filters"] == {"tags": "new"}
|
||||
def test_create_duplicate_name(self, client: TestClient):
|
||||
"""POST /api/saved-searches with duplicate name returns 409."""
|
||||
payload = {"name": "My Search", "filters": {"status": "completed"}}
|
||||
response1 = client.post("/api/saved-searches", json=payload)
|
||||
assert response1.status_code == 201
|
||||
|
||||
def test_update_saved_search_not_found(self, int_client):
|
||||
"""Updating a non-existent search returns 404."""
|
||||
update_payload = {"name": "Updated Name"}
|
||||
resp = int_client.put("/api/saved-searches/999", json=update_payload)
|
||||
assert resp.status_code == 404
|
||||
response2 = client.post("/api/saved-searches", json=payload)
|
||||
assert response2.status_code == 409
|
||||
|
||||
def test_update_saved_search_duplicate_name(self, int_client):
|
||||
"""Updating name to an existing search name returns 409."""
|
||||
payload1 = {"name": "Search 1", "filters": {"q": "a"}}
|
||||
payload2 = {"name": "Search 2", "filters": {"q": "b"}}
|
||||
int_client.post("/api/saved-searches", json=payload1)
|
||||
created2 = int_client.post("/api/saved-searches", json=payload2).json()
|
||||
search2_id = created2["id"]
|
||||
def test_update_saved_search(self, client: TestClient):
|
||||
"""PUT /api/saved-searches/{id} updates the saved search."""
|
||||
# Create
|
||||
create_resp = client.post(
|
||||
"/api/saved-searches",
|
||||
json={"name": "Original", "filters": {"status": "pending"}},
|
||||
)
|
||||
search_id = create_resp.json()["id"]
|
||||
|
||||
update_payload = {"name": "Search 1"}
|
||||
resp = int_client.put(f"/api/saved-searches/{search2_id}", json=update_payload)
|
||||
assert resp.status_code == 409
|
||||
# Update
|
||||
update_resp = client.put(
|
||||
f"/api/saved-searches/{search_id}",
|
||||
json={"name": "Updated", "filters": {"status": "completed"}},
|
||||
)
|
||||
assert update_resp.status_code == 200
|
||||
data = update_resp.json()
|
||||
assert data["name"] == "Updated"
|
||||
assert data["filters"]["status"] == "completed"
|
||||
|
||||
def test_delete_saved_search(self, int_client, int_session):
|
||||
"""Delete an existing search."""
|
||||
payload = {"name": "To be deleted", "filters": {"q": "test"}}
|
||||
created = int_client.post("/api/saved-searches", json=payload).json()
|
||||
search_id = created["id"]
|
||||
def test_update_saved_search_not_found(self, client: TestClient):
|
||||
"""PUT /api/saved-searches/999 returns 404."""
|
||||
response = client.put(
|
||||
"/api/saved-searches/999",
|
||||
json={"name": "Nope", "filters": {"status": "completed"}},
|
||||
)
|
||||
assert response.status_code == 404
|
||||
|
||||
resp = int_client.delete(f"/api/saved-searches/{search_id}")
|
||||
assert resp.status_code == 204
|
||||
def test_delete_saved_search(self, client: TestClient):
|
||||
"""DELETE /api/saved-searches/{id} removes the saved search."""
|
||||
# Create
|
||||
create_resp = client.post(
|
||||
"/api/saved-searches",
|
||||
json={"name": "To Delete", "filters": {"status": "failed"}},
|
||||
)
|
||||
search_id = create_resp.json()["id"]
|
||||
|
||||
assert int_session.query(SavedSearch).filter(SavedSearch.id == search_id).first() is None
|
||||
# Delete
|
||||
del_resp = client.delete(f"/api/saved-searches/{search_id}")
|
||||
assert del_resp.status_code == 204
|
||||
|
||||
def test_delete_saved_search_not_found(self, int_client):
|
||||
"""Deleting a non-existent search returns 404."""
|
||||
resp = int_client.delete("/api/saved-searches/999")
|
||||
assert resp.status_code == 404
|
||||
# Verify it's gone
|
||||
list_resp = client.get("/api/saved-searches")
|
||||
assert len(list_resp.json()) == 0
|
||||
|
||||
def test_other_users_searches_isolated(self, int_engine, int_session):
|
||||
"""Users only see and can only modify their own saved searches."""
|
||||
int_session.add(SavedSearch(user_id=_OTHER_OWNER, name="Other Search", filters='{"q": "test"}'))
|
||||
int_session.commit()
|
||||
def test_delete_saved_search_not_found(self, client: TestClient):
|
||||
"""DELETE /api/saved-searches/999 returns 404."""
|
||||
response = client.delete("/api/saved-searches/999")
|
||||
assert response.status_code == 404
|
||||
|
||||
client = next(_make_client(int_engine, _OWNER))
|
||||
resp = client.get("/api/saved-searches")
|
||||
assert resp.status_code == 200
|
||||
assert len(resp.json()) == 0
|
||||
def test_create_name_too_long(self, client: TestClient):
|
||||
"""POST /api/saved-searches with name > 100 chars returns 422."""
|
||||
payload = {
|
||||
"name": "x" * 101,
|
||||
"filters": {"status": "completed"},
|
||||
}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
assert response.status_code == 422
|
||||
|
||||
other_search = int_session.query(SavedSearch).first()
|
||||
resp = client.put(f"/api/saved-searches/{other_search.id}", json={"name": "Hacked"})
|
||||
assert resp.status_code == 404
|
||||
def test_saved_search_filters_sanitized(self, client: TestClient):
|
||||
"""Saved search filters are sanitized to allowed keys only."""
|
||||
payload = {
|
||||
"name": "Sanitized",
|
||||
"filters": {
|
||||
"search": "invoice",
|
||||
"mime_type": "application/pdf",
|
||||
"date_from": "2026-01-01",
|
||||
"date_to": "2026-12-31",
|
||||
"storage_provider": "dropbox",
|
||||
"tags": "invoice,amazon",
|
||||
"sort_by": "created_at",
|
||||
"sort_order": "desc",
|
||||
},
|
||||
}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
assert response.status_code == 201
|
||||
data = response.json()
|
||||
assert len(data["filters"]) == 8
|
||||
assert data["filters"]["search"] == "invoice"
|
||||
assert data["filters"]["tags"] == "invoice,amazon"
|
||||
|
||||
resp = client.delete(f"/api/saved-searches/{other_search.id}")
|
||||
assert resp.status_code == 404
|
||||
def test_saved_search_with_fulltext_query(self, client: TestClient):
|
||||
"""Saved search can include full-text query (q) for the search view."""
|
||||
payload = {
|
||||
"name": "Invoice Search",
|
||||
"filters": {"q": "invoice total amount", "document_type": "Invoice"},
|
||||
}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
assert response.status_code == 201
|
||||
data = response.json()
|
||||
assert data["filters"]["q"] == "invoice total amount"
|
||||
assert data["filters"]["document_type"] == "Invoice"
|
||||
|
||||
def test_saved_search_content_finding_filters(self, client: TestClient):
|
||||
"""Saved search accepts content-finding filter keys (language, sender, text_quality)."""
|
||||
payload = {
|
||||
"name": "German Invoices",
|
||||
"filters": {
|
||||
"q": "rechnung",
|
||||
"language": "de",
|
||||
"sender": "ACME GmbH",
|
||||
"text_quality": "high",
|
||||
"tags": "invoice",
|
||||
},
|
||||
}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
assert response.status_code == 201
|
||||
data = response.json()
|
||||
assert data["filters"]["q"] == "rechnung"
|
||||
assert data["filters"]["language"] == "de"
|
||||
assert data["filters"]["sender"] == "ACME GmbH"
|
||||
assert data["filters"]["text_quality"] == "high"
|
||||
assert data["filters"]["tags"] == "invoice"
|
||||
|
||||
def test_create_saved_search_max_limit(self, client: TestClient, db_session, mocker):
|
||||
"""POST /api/saved-searches returns 409 when max limit is reached."""
|
||||
from app.api.saved_searches import MAX_SAVED_SEARCHES_PER_USER
|
||||
|
||||
user_id = "test_user"
|
||||
mocker.patch("app.api.saved_searches._get_user_id", return_value=user_id)
|
||||
|
||||
for i in range(MAX_SAVED_SEARCHES_PER_USER):
|
||||
search = SavedSearch(user_id=user_id, name=f"Search {i}", filters="""{"tags": "invoice"}""")
|
||||
db_session.add(search)
|
||||
db_session.commit()
|
||||
|
||||
payload = {
|
||||
"name": "One More",
|
||||
"filters": {"tags": "invoice"},
|
||||
}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
assert response.status_code == 409
|
||||
|
||||
def test_create_saved_search_db_error(self, client: TestClient, mocker):
|
||||
"""POST /api/saved-searches handles db.commit errors gracefully."""
|
||||
mocker.patch("sqlalchemy.orm.Session.commit", side_effect=Exception("DB Error"))
|
||||
payload = {
|
||||
"name": "Fail Me",
|
||||
"filters": {"tags": "invoice"},
|
||||
}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
assert response.status_code == 500
|
||||
|
||||
def test_update_saved_search_db_error(self, client: TestClient, mocker):
|
||||
"""PUT /api/saved-searches/{id} handles db.commit errors gracefully."""
|
||||
# Create a search first
|
||||
payload = {
|
||||
"name": "Update Target",
|
||||
"filters": {"tags": "invoice"},
|
||||
}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
search_id = response.json()["id"]
|
||||
|
||||
mocker.patch("sqlalchemy.orm.Session.commit", side_effect=Exception("DB Error"))
|
||||
update_payload = {"name": "New Name"}
|
||||
response = client.put(f"/api/saved-searches/{search_id}", json=update_payload)
|
||||
assert response.status_code == 500
|
||||
|
||||
def test_delete_saved_search_db_error(self, client: TestClient, mocker):
|
||||
"""DELETE /api/saved-searches/{id} handles db.commit errors gracefully."""
|
||||
# Create a search first
|
||||
payload = {
|
||||
"name": "Delete Target",
|
||||
"filters": {"tags": "invoice"},
|
||||
}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
search_id = response.json()["id"]
|
||||
|
||||
mocker.patch("sqlalchemy.orm.Session.commit", side_effect=Exception("DB Error"))
|
||||
response = client.delete(f"/api/saved-searches/{search_id}")
|
||||
assert response.status_code == 500
|
||||
|
||||
def test_update_saved_search_name_conflict(self, client: TestClient):
|
||||
"""PUT /api/saved-searches/{id} returns 409 when the new name conflicts with an existing search."""
|
||||
# Create search 1
|
||||
payload1 = {"name": "Search One", "filters": {"tags": "invoice"}}
|
||||
client.post("/api/saved-searches", json=payload1)
|
||||
|
||||
# Create search 2
|
||||
payload2 = {"name": "Search Two", "filters": {"status": "completed"}}
|
||||
response2 = client.post("/api/saved-searches", json=payload2)
|
||||
search2_id = response2.json()["id"]
|
||||
|
||||
# Try to update search 2 to have name "Search One"
|
||||
update_payload = {"name": "Search One"}
|
||||
response = client.put(f"/api/saved-searches/{search2_id}", json=update_payload)
|
||||
assert response.status_code == 409
|
||||
|
||||
def test_update_saved_search_empty_filters(self, client: TestClient):
|
||||
"""PUT /api/saved-searches/{id} returns 422 if filters are empty or invalid."""
|
||||
payload = {"name": "Search XYZ", "filters": {"tags": "invoice"}}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
search_id = response.json()["id"]
|
||||
|
||||
# Empty filters
|
||||
update_payload = {"filters": {}}
|
||||
response = client.put(f"/api/saved-searches/{search_id}", json=update_payload)
|
||||
assert response.status_code == 422
|
||||
|
||||
# Invalid keys
|
||||
update_payload = {"filters": {"invalid_key": "value"}}
|
||||
response = client.put(f"/api/saved-searches/{search_id}", json=update_payload)
|
||||
assert response.status_code == 422
|
||||
|
||||
def test_update_saved_search_invalid_name(self, client: TestClient):
|
||||
"""PUT /api/saved-searches/{id} returns 422 if name is invalid or too long."""
|
||||
payload = {"name": "Search XYZ", "filters": {"tags": "invoice"}}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
search_id = response.json()["id"]
|
||||
|
||||
# Empty name
|
||||
update_payload = {"name": ""}
|
||||
response = client.put(f"/api/saved-searches/{search_id}", json=update_payload)
|
||||
assert response.status_code == 422
|
||||
|
||||
# Too long name
|
||||
update_payload = {"name": "A" * 101}
|
||||
response = client.put(f"/api/saved-searches/{search_id}", json=update_payload)
|
||||
assert response.status_code == 422
|
||||
|
||||
def test_update_saved_search_same_name(self, client: TestClient):
|
||||
"""PUT /api/saved-searches/{id} with the same name does not trigger duplicate check error."""
|
||||
# Create a search
|
||||
payload = {"name": "Same Name", "filters": {"tags": "invoice"}}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
search_id = response.json()["id"]
|
||||
|
||||
# Update with the exact same name
|
||||
update_payload = {"name": "Same Name"}
|
||||
response = client.put(f"/api/saved-searches/{search_id}", json=update_payload)
|
||||
assert response.status_code == 200
|
||||
assert response.json()["name"] == "Same Name"
|
||||
|
||||
def test_get_user_id_branches_real(self, client: TestClient):
|
||||
from app.api.saved_searches import _get_user_id
|
||||
|
||||
# We need a mock request
|
||||
class MockRequest:
|
||||
session = {}
|
||||
state = type("obj", (object,), {"user": None})
|
||||
|
||||
req = MockRequest()
|
||||
assert _get_user_id(req) == "anonymous"
|
||||
|
||||
req.session["user"] = {"preferred_username": "pref"}
|
||||
assert _get_user_id(req) == "pref"
|
||||
|
||||
req.session["user"] = {"email": "em@il.com"}
|
||||
assert _get_user_id(req) == "em@il.com"
|
||||
|
||||
req.session["user"] = {"name": "named"}
|
||||
assert _get_user_id(req) == "named"
|
||||
|
||||
req.session["user"] = {}
|
||||
assert _get_user_id(req) == "anonymous"
|
||||
|
||||
def test_validate_filters_not_dict(self, client: TestClient):
|
||||
"""POST /api/saved-searches with non-dict filters returns 422."""
|
||||
payload = {
|
||||
"name": "Invalid Filters",
|
||||
"filters": "not a dict",
|
||||
}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
assert response.status_code == 422
|
||||
|
||||
def test_create_saved_search_non_dict_filters(self, client: TestClient):
|
||||
payload = {"name": "Test", "filters": []}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
assert response.status_code == 422
|
||||
|
||||
def test_update_saved_search_non_dict_filters(self, client: TestClient):
|
||||
payload = {"name": "Test", "filters": {"tags": "invoice"}}
|
||||
response = client.post("/api/saved-searches", json=payload)
|
||||
search_id = response.json()["id"]
|
||||
|
||||
update_payload = {"filters": []}
|
||||
response = client.put(f"/api/saved-searches/{search_id}", json=update_payload)
|
||||
assert response.status_code == 422
|
||||
|
||||
+3
-3
@@ -430,8 +430,8 @@ class TestLoginFunction:
|
||||
# Verify TemplateResponse was called with correct context
|
||||
mock_templates.TemplateResponse.assert_called_once()
|
||||
call_args = mock_templates.TemplateResponse.call_args
|
||||
assert call_args[0][0] == "login.html"
|
||||
context = call_args[0][1]
|
||||
assert call_args[0][1] == "login.html"
|
||||
context = call_args.kwargs["context"]
|
||||
assert context["error"] == "Test error"
|
||||
assert context["message"] == "Test message"
|
||||
|
||||
@@ -450,7 +450,7 @@ class TestLoginFunction:
|
||||
|
||||
mock_templates.TemplateResponse.assert_called_once()
|
||||
call_args = mock_templates.TemplateResponse.call_args
|
||||
context = call_args[0][1]
|
||||
context = call_args.kwargs["context"]
|
||||
assert context["error"] is None
|
||||
assert context["message"] is None
|
||||
|
||||
|
||||
@@ -281,7 +281,7 @@ class TestLoginEndpoint:
|
||||
# Verify template was rendered with OAuth enabled
|
||||
mock_templates.TemplateResponse.assert_called_once()
|
||||
call_args = mock_templates.TemplateResponse.call_args
|
||||
context = call_args[0][1]
|
||||
context = call_args.kwargs["context"]
|
||||
assert context["show_oauth"] is True
|
||||
assert context["oauth_provider_name"] == "Test SSO"
|
||||
|
||||
|
||||
@@ -35,6 +35,7 @@ class TestValidateStorageConfigs:
|
||||
"google_drive",
|
||||
"onedrive",
|
||||
"email",
|
||||
"evernote",
|
||||
"paperless",
|
||||
"uptime_kuma",
|
||||
]
|
||||
@@ -83,6 +84,13 @@ class TestValidateStorageConfigs:
|
||||
assert "DEST_EMAIL_HOST is not configured" in result["email"]
|
||||
assert "DEST_EMAIL_DEFAULT_RECIPIENT is not configured" in result["email"]
|
||||
|
||||
def test_evernote_missing_token(self):
|
||||
"""Test validation when Evernote destination auth token is missing."""
|
||||
with patch("app.utils.config_validator.validators.settings") as mock_settings:
|
||||
mock_settings.evernote_auth_token = None
|
||||
result = validate_storage_configs()
|
||||
assert "EVERNOTE_AUTH_TOKEN is not configured" in result["evernote"]
|
||||
|
||||
|
||||
@pytest.mark.unit
|
||||
class TestValidateEmailConfig:
|
||||
|
||||
@@ -520,14 +520,14 @@ class TestURLUploadAdditionalCoverage:
|
||||
assert exc_info.value.status_code == 400
|
||||
|
||||
def test_is_private_ip_unresolvable_hostname(self):
|
||||
"""Cover DNS resolution failure branch (lines 67-72)."""
|
||||
"""Cover DNS resolution failure branch blocking unresolvable domains."""
|
||||
import socket as _socket
|
||||
|
||||
from app.utils.network import is_private_ip
|
||||
|
||||
with patch("socket.getaddrinfo", side_effect=_socket.gaierror("nope")):
|
||||
result = is_private_ip("nonexistent.invalid.hostname.test")
|
||||
assert result is False
|
||||
assert result is True # Fail securely by returning True
|
||||
|
||||
def test_is_private_ip_hostname_resolves_to_private(self):
|
||||
"""Cover branch where hostname resolves to a private IP (line 64-65)."""
|
||||
|
||||
@@ -69,8 +69,8 @@ class TestViewsBase:
|
||||
context = {"request": req}
|
||||
template_response_with_version("template.html", context)
|
||||
|
||||
args, _ = mock_orig.call_args
|
||||
assert args[1].get("csrf_token") == "my-csrf"
|
||||
_, kwargs = mock_orig.call_args
|
||||
assert kwargs["context"].get("csrf_token") == "my-csrf"
|
||||
|
||||
def test_kwargs_context_no_request(self):
|
||||
"""Test kwargs context path when request is not in context."""
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user