Merge pull request #77 from internetarchive/spring-2024

Merging spring 2024 fixes

.gitignore

@@ -58,3 +58,12 @@ docs/_build/
 
 # PyBuilder
 target/
+
+# Cache dir
+cache/
+
+# PyCharm
+.idea/
+
+# Old folder from v2?
+media/

README.md

@@ -39,6 +39,11 @@ Unit tests are in the `tests` folder and can be run with:
 python -m unittest discover -s tests
 ```
 
+Run single test:
+```
+python -m unittest tests.test_video.TestVideo.test_vtt_autogenerated
+```
+
 Retrieve large.jpg as 800px wide JPEG
 * http://127.0.0.1:8080/iiif/large.jpg/full/800,/0/default.jpg 
 

iiify/app.py

@@ -8,7 +8,7 @@
 from flask_caching import Cache
 from iiif2 import iiif, web
 from .resolver import ia_resolver, create_manifest, create_manifest3, getids, collection, \
-    purify_domain, cantaloupe_resolver, create_collection3, IsCollection
+    purify_domain, cantaloupe_resolver, create_collection3, IsCollection, create_annotations
 from .configs import options, cors, approot, cache_root, media_root, \
     cache_expr, version, image_server, cache_timeouts
 from urllib.parse import quote
@@ -17,7 +17,7 @@
 app = Flask(__name__)
 # disabling sorting of the output json
 app.config['JSON_SORT_KEYS'] = False
-app.config['CACHE_TYPE'] = "FileSystemCache"
+app.config['CACHE_TYPE'] = "FileSystemCache" if os.environ.get("FLASK_CACHE_DISABLE", None) != "true" else "NullCache"
 app.config['CACHE_DIR'] = "cache"
 cors = CORS(app) if cors else None
 cache = Cache(app)
@@ -191,6 +191,11 @@ def manifest3(identifier):
         raise excpt
         # abort(404)
 
+@app.route('/iiif/<version>/annotations/<identifier>/<fileName>/<canvas_no>.json')
+@cache.cached(timeout=cache_timeouts["long"], forced_update=cache_bust)
+def annnotations(version, identifier, fileName, canvas_no):
+    domain = purify_domain(request.args.get('domain', request.url_root))
+    return ldjsonify(create_annotations(version, identifier, fileName, canvas_no, domain=domain))
 
 @app.route('/iiif/<identifier>/manifest.json')
 @cache.cached(timeout=cache_timeouts["long"], forced_update=cache_bust)
@@ -199,7 +204,7 @@ def manifest(identifier):
 
 @app.route('/iiif/2/<identifier>/manifest.json')
 def manifest2(identifier):
-    domain = "https://iiif.archivelab.org/iiif/"
+    domain = purify_domain(request.args.get('domain', request.url_root))
     page = None
     if '$' in identifier:
         identifier, page = identifier.split('$')

iiify/configs/__init__.py

@@ -14,6 +14,7 @@
 import sys
 import types
 import configparser
+import json
 
 path = os.path.dirname(os.path.realpath(__file__))
 approot = os.path.abspath(os.path.join(path, os.pardir))
@@ -75,3 +76,6 @@ def getdef(self, section, option, default_value):
     "long": 432000,  # 5 days
     "longest": 2592000  # 30 days
 }
+
+with open('%s/links.json' % path, 'r') as file:
+    LINKS = json.load(file)

iiify/configs/links.json

@@ -0,0 +1,137 @@
+{
+    "Animated GIF": {
+        "field": "rendering",
+        "type": "Image",
+        "format": "image/gif"
+    },
+    "Text PDF": {
+	    "field": "rendering",
+        "type": "Text",
+        "format": "application/pdf"
+    },
+    "Abbyy GZ": {
+        "field": "rendering",
+        "type": "Dataset",
+        "format": "application/gzip"
+    },
+    "Archive BitTorrent": {
+        "field": "rendering",
+        "type": "Dataset",
+        "format": "application/x-bittorrent"
+    },
+    "Grayscale PDF": {
+        "field": "rendering",
+        "type": "Text",
+        "format": "application/pdf"
+    },
+    "chOCR": {
+        "field": "rendering",
+        "type": "Text",
+        "format": "application/gzip"
+    },
+    "DjVuTXT": {
+        "field": "rendering",
+        "type": "Text",
+        "format": "text/plain"
+    },
+    "Djvu XML": {
+        "field": "rendering",
+        "type": "Dataset",
+        "format": "application/xml"
+    },
+    "hOCR": {
+        "field": "rendering",
+        "type": "Text",
+        "format": "text/html"
+    },
+    "Single Page Processed JP2 ZIP": {
+        "field": "rendering",
+        "type": "Image",
+        "format": "application/zip"
+    },
+    "OCR Search Text": {
+        "field": "rendering",
+        "type": "Text",
+        "format": "application/gzip"
+    },
+    "Single Page Original JP2 Tar": {
+        "field": "rendering",
+        "type": "Image",
+        "format": "application/x-tar"
+    },
+    "DjVu": {
+        "field": "rendering",
+        "type": "Image",
+        "format": "image/vnd.djvu"
+    },
+    "Cloth Cover Detection Log": {
+        "field": "seeAlso",
+        "type": "Text",
+        "format": "text/plain"
+    },
+    "Dublin Core": {
+        "field": "seeAlso",
+        "type": "Dataset",
+        "format": "application/xml"
+    },
+    "OCR Page Index": {
+        "field": "seeAlso",
+        "type": "Dataset",
+        "format": "application/json"
+    },
+    "MARC": {
+        "field": "seeAlso",
+        "type": "Dataset",
+        "format": "application/xml"
+    },
+    "MARC Binary": {
+        "field": "seeAlso",
+        "type": "Dataset",
+        "format": "application/marc"
+    },
+    "MARC Source": {
+        "field": "seeAlso",
+        "type": "Dataset",
+        "format": "application/xml"
+    },
+    "Page Numbers JSON": {
+        "field": "seeAlso",
+        "type": "Dataset",
+        "format": "application/json"
+    },
+    "Scandata": {
+        "field": "seeAlso",
+        "type": "Dataset",
+        "format": "application/xml"
+    },
+    "SubRip": {
+        "field": "rendering",
+        "type": "Text",
+        "format": "text/plain"
+    },
+    "Web Video Text Tracks": {
+        "field": "rendering",
+        "type": "Text",
+        "format": "text/vtt"
+    },
+    "Intermediate ASR JSON": {
+        "field": "rendering",
+        "type": "Text",
+        "format": "application/json"
+    },
+    "Whisper ASR JSON": {
+        "field": "rendering",
+        "type": "Text",
+        "format": "application/json"
+    },
+    "Storj Upload Log": {
+        "field": "seeAlso",
+        "type": "Text",
+        "format": "text/plain"
+    },
+    "Storj Upload Trigger": {
+        "field": "seeAlso",
+        "type": "Text",
+        "format": "text/plain"
+    }
+}