Extract filename parsing into testable class

src/documents/models.py

@@ -23,9 +23,72 @@ class FileInfo(object):
         self._file_mtime = file_mtime
         self._path = path
 
+    REGEX_TITLE = re.compile(
+        r"^.*/(.*)\.(pdf|jpe?g|png|gif|tiff)$",
+        flags=re.IGNORECASE
+    )
+    REGEX_CORRESPONDENT_TITLE = re.compile(
+        r"^.*/(.+) - (.*)\.(pdf|jpe?g|png|gif|tiff)$",
+        flags=re.IGNORECASE
+    )
+    REGEX_CORRESPONDENT_TITLE_TAGS = re.compile(
+        r"^.*/(.*) - (.*) - ([a-z0-9\-,]*)\.(pdf|jpe?g|png|gif|tiff)$",
+        flags=re.IGNORECASE
+    )
+
     @classmethod
     def from_path(cls, path):
-        pass
+        """
+        We use a crude naming convention to make handling the correspondent,
+        title, and tags easier:
+          "<correspondent> - <title> - <tags>.<suffix>"
+          "<correspondent> - <title>.<suffix>"
+          "<title>.<suffix>"
+        """
+
+        def get_correspondent(correspondent_name):
+            return Correspondent.objects.get_or_create(
+                name=correspondent_name,
+                defaults={"slug": slugify(correspondent_name)}
+            )[0]
+
+        def get_tags(tags):
+            r = []
+            for t in tags.split(","):
+                r.append(
+                    Tag.objects.get_or_create(slug=t, defaults={"name": t})[0])
+            return tuple(r)
+
+        def get_suffix(suffix):
+            suffix = suffix.lower()
+            if suffix == "jpeg":
+                return "jpg"
+            return suffix
+
+        # First attempt: "<correspondent> - <title> - <tags>.<suffix>"
+        m = re.match(cls.REGEX_CORRESPONDENT_TITLE_TAGS, path)
+        if m:
+            return cls(
+                title=m.group(2),
+                correspondent=get_correspondent(m.group(1)),
+                tags=get_tags(m.group(3)),
+                suffix=get_suffix(m.group(4))
+            )
+
+        # Second attempt: "<correspondent> - <title>.<suffix>"
+        m = re.match(cls.REGEX_CORRESPONDENT_TITLE, path)
+        if m:
+            return cls(
+                title=m.group(2),
+                correspondent=get_correspondent(m.group(1)),
+                tags=(),
+                suffix=get_suffix(m.group(3))
+            )
+
+        # That didn't work, so we assume correspondent and tags are None
+        m = re.match(cls.REGEX_TITLE, path)
+        return FileInfo(
+            title=m.group(1), tags=(), suffix=get_suffix(m.group(2)))
 
     @classmethod
     def from_document(cls, document):