feat(parsers): add generator for date parsing

diff --git a/src/documents/parsers.py b/src/documents/parsers.py
index 721346fb0667b7cf3375aaecbc9676c8800be692..26a4e11c65fab77fa74bb9a5485c53d599332d2a 100644 (file)
--- a/src/documents/parsers.py
+++ b/src/documents/parsers.py
@@ -6,6 +6,7 @@ import re
 import shutil
 import subprocess
 import tempfile
+from typing import Iterator
 from typing import Optional
 from typing import Set
 
@@ -216,6 +217,10 @@ def make_thumbnail_from_pdf(in_path, temp_dir, logging_group=None) -> str:
 
 
 def parse_date(filename, text) -> Optional[datetime.datetime]:
+    return next(parse_date_generator(filename, text), None)
+
+
+def parse_date_generator(filename, text) -> Iterator[datetime.datetime]:
     """
     Returns the date of the document.
     """
@@ -246,38 +251,32 @@ def parse_date(filename, text) -> Optional[datetime.datetime]:
             return date
         return None
 
-    date = None
-
-    # if filename date parsing is enabled, search there first:
-    if settings.FILENAME_DATE_ORDER:
-        for m in re.finditer(DATE_REGEX, filename):
-            date_string = m.group(0)
-
-            try:
-                date = __parser(date_string, settings.FILENAME_DATE_ORDER)
-            except (TypeError, ValueError):
-                # Skip all matches that do not parse to a proper date
-                continue
-
-            date = __filter(date)
-            if date is not None:
-                return date
-
-    # Iterate through all regex matches in text and try to parse the date
-    for m in re.finditer(DATE_REGEX, text):
-        date_string = m.group(0)
+    def __process_match(
+        match: re.Match[str],
+        date_order: str,
+    ) -> Optional[datetime.datetime]:
+        date_string = match.group(0)
 
         try:
-            date = __parser(date_string, settings.DATE_ORDER)
+            date = __parser(date_string, date_order)
         except (TypeError, ValueError):
             # Skip all matches that do not parse to a proper date
-            continue
+            date = None
 
-        date = __filter(date)
-        if date is not None:
-            return date
+        return __filter(date)
+
+    def __process_content(content: str, date_order: str) -> Iterator[datetime.datetime]:
+        for m in re.finditer(DATE_REGEX, content):
+            date = __process_match(m, date_order)
+            if date is not None:
+                yield date
 
-    return date
+    # if filename date parsing is enabled, search there first:
+    if settings.FILENAME_DATE_ORDER:
+        yield from __process_content(filename, settings.FILENAME_DATE_ORDER)
+
+    # Iterate through all regex matches in text and try to parse the date
+    yield from __process_content(text, settings.DATE_ORDER)
 
 
 class ParseError(Exception):

diff --git a/src/documents/views.py b/src/documents/views.py
index 84fc38a38a4bd24117be2e85c1068c3e881e85ef..f0061cf2b3ce3964c9ba6654e86512acd7117cc6 100644 (file)
--- a/src/documents/views.py
+++ b/src/documents/views.py
@@ -1,3 +1,4 @@
+import itertools
 import json
 import logging
 import os
@@ -21,6 +22,7 @@ from django.db.models.functions import Lower
 from django.http import Http404
 from django.http import HttpResponse
 from django.http import HttpResponseBadRequest
+from django.shortcuts import get_object_or_404
 from django.utils.decorators import method_decorator
 from django.utils.translation import get_language
 from django.views.decorators.cache import cache_control
@@ -70,6 +72,7 @@ from .models import SavedView
 from .models import StoragePath
 from .models import Tag
 from .parsers import get_parser_class_for_mime_type
+from .parsers import parse_date_generator
 from .serialisers import AcknowledgeTasksViewSerializer
 from .serialisers import BulkDownloadSerializer
 from .serialisers import BulkEditSerializer
@@ -329,13 +332,13 @@ class DocumentViewSet(
 
     @action(methods=["get"], detail=True)
     def suggestions(self, request, pk=None):
-        try:
-            doc = Document.objects.get(pk=pk)
-        except Document.DoesNotExist:
-            raise Http404()
+        doc = get_object_or_404(Document, pk=pk)
 
         classifier = load_classifier()
 
+        gen = parse_date_generator(doc.filename, doc.content)
+        dates = {i for i in itertools.islice(gen, 5)}
+
         return Response(
             {
                 "correspondents": [c.id for c in match_correspondents(doc, classifier)],
@@ -344,6 +347,9 @@ class DocumentViewSet(
                     dt.id for dt in match_document_types(doc, classifier)
                 ],
                 "storage_paths": [dt.id for dt in match_storage_paths(doc, classifier)],
+                "dates": [
+                    date.strftime("%Y-%m-%d") for date in dates if date is not None
+                ],
             },
         )