explicitly add txt, md, and csv types for consumer and viewer; fix thumbnail generation

src/documents/models.py

@@ -188,7 +188,11 @@ class Document(models.Model):
     TYPE_JPG = "jpg"
     TYPE_GIF = "gif"
     TYPE_TIF = "tiff"
-    TYPES = (TYPE_PDF, TYPE_PNG, TYPE_JPG, TYPE_GIF, TYPE_TIF,)
+    TYPE_TXT = "txt"
+    TYPE_CSV = "csv"
+    TYPE_MD  = "md"
+    TYPES = (TYPE_PDF, TYPE_PNG, TYPE_JPG, TYPE_GIF, TYPE_TIF,
+             TYPE_TXT, TYPE_CSV, TYPE_MD)
 
     STORAGE_TYPE_UNENCRYPTED = "unencrypted"
     STORAGE_TYPE_GPG = "gpg"
@@ -361,51 +365,52 @@ class FileInfo:
         )
     )
 
+    formats = "pdf|jpe?g|png|gif|tiff?|te?xt|md|csv"
     REGEXES = OrderedDict([
         ("created-correspondent-title-tags", re.compile(
             r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
             r"(?P<correspondent>.*) - "
             r"(?P<title>.*) - "
             r"(?P<tags>[a-z0-9\-,]*)"
-            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
+            r"\.(?P<extension>{})$".format(formats),
             flags=re.IGNORECASE
         )),
         ("created-title-tags", re.compile(
             r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
             r"(?P<title>.*) - "
             r"(?P<tags>[a-z0-9\-,]*)"
-            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
+            r"\.(?P<extension>{})$".format(formats),
             flags=re.IGNORECASE
         )),
         ("created-correspondent-title", re.compile(
             r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
             r"(?P<correspondent>.*) - "
             r"(?P<title>.*)"
-            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
+            r"\.(?P<extension>{})$".format(formats),
             flags=re.IGNORECASE
         )),
         ("created-title", re.compile(
             r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
             r"(?P<title>.*)"
-            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
+            r"\.(?P<extension>{})$".format(formats),
             flags=re.IGNORECASE
         )),
         ("correspondent-title-tags", re.compile(
             r"(?P<correspondent>.*) - "
             r"(?P<title>.*) - "
             r"(?P<tags>[a-z0-9\-,]*)"
-            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
+            r"\.(?P<extension>{})$".format(formats),
             flags=re.IGNORECASE
         )),
         ("correspondent-title", re.compile(
             r"(?P<correspondent>.*) - "
             r"(?P<title>.*)?"
-            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
+            r"\.(?P<extension>{})$".format(formats),
             flags=re.IGNORECASE
         )),
         ("title", re.compile(
             r"(?P<title>.*)"
-            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
+            r"\.(?P<extension>{})$".format(formats),
             flags=re.IGNORECASE
         ))
     ])

src/documents/views.py

@@ -48,6 +48,9 @@ class FetchView(SessionOrBasicAuthMixin, DetailView):
             Document.TYPE_JPG: "image/jpeg",
             Document.TYPE_GIF: "image/gif",
             Document.TYPE_TIF: "image/tiff",
+            Document.TYPE_CSV: "text/csv",
+            Document.TYPE_MD:  "text/markdown",
+            Document.TYPE_TXT: "text/plain"
         }
 
         if self.kwargs["kind"] == "thumb":

src/paperless_text/parsers.py

@@ -10,7 +10,7 @@ from documents.parsers import DocumentParser, ParseError
 
 class TextDocumentParser(DocumentParser):
     """
-    This parser directly parses a text document (.txt or .md)
+    This parser directly parses a text document (.txt, .md, or .csv)
     """
 
 
@@ -30,18 +30,50 @@ class TextDocumentParser(DocumentParser):
         The thumbnail of a txt is just a 500px wide image of the text
         rendered onto a letter-sized page.
         """
+        # The below is heavily cribbed from https://askubuntu.com/a/590951
 
-        run_convert(
+        bg_color = "white"  # bg color
-            self.CONVERT,
+        text_color = "black"  # text color
-            "-size", "500x647",
+        psize = [500, 647]  # icon size
-            "xc:white",
+        n_lines = 50  # number of lines to show
-            "-pointsize", "12",
+        output_file = os.path.join(self.tempdir, "convert-txt.png")
-            "-fill", "black",
-            "-draw", "\"text 0,12 \'$(cat {})\'\"".format(self.document_path),
-            os.path.join(self.tempdir, "convert-txt.png")
-        )
 
-        return os.path.join(self.tempdir, "convert-txt.png")
+        temp_bg = os.path.join(self.tempdir, "bg.png")
+        temp_txlayer = os.path.join(self.tempdir, "tx.png")
+        picsize = "x".join([str(n) for n in psize])
+        txsize = "x".join([str(n - 8) for n in psize])
+
+        def create_bg():
+            work_size = ",".join([str(n - 1) for n in psize])
+            r = str(round(psize[0] / 10));
+            rounded = ",".join([r, r])
+            run_command(self.CONVERT, "-size ", picsize, ' xc:none -draw ',
+                        '"fill ', bg_color, ' roundrectangle 0,0,',
+                        work_size, ",", rounded, '" ', temp_bg)
+
+        def read_text():
+            with open(self.document_path, 'r') as src:
+                lines = [l.strip() for l in src.readlines()]
+                text = "\n".join([l for l in lines[:n_lines]])
+                return text.replace('"', "'")
+
+        def create_txlayer():
+            run_command(self.CONVERT,
+                        "-background none",
+                        "-fill",
+                        text_color,
+                        "-pointsize", "12",
+                        "-border 4 -bordercolor none",
+                        "-size ", txsize,
+                        ' caption:"', read_text(), '" ',
+                        temp_txlayer)
+
+        create_txlayer()
+        create_bg()
+        run_command(self.CONVERT, temp_bg, temp_txlayer,
+                    "-background None -layers merge ", output_file)
+
+        return output_file
 
     def get_text(self):
 
@@ -102,12 +134,13 @@ class TextDocumentParser(DocumentParser):
         return date
 
 
-def run_convert(*args):
+def run_command(*args):
     environment = os.environ.copy()
     if settings.CONVERT_MEMORY_LIMIT:
         environment["MAGICK_MEMORY_LIMIT"] = settings.CONVERT_MEMORY_LIMIT
     if settings.CONVERT_TMPDIR:
         environment["MAGICK_TMPDIR"] = settings.CONVERT_TMPDIR
 
-    if not subprocess.Popen(args, env=environment).wait() == 0:
+    if not subprocess.Popen(' '.join(args), env=environment,
+                            shell=True).wait() == 0:
         raise ParseError("Convert failed at {}".format(args))

src/paperless_text/signals.py

@@ -5,7 +5,7 @@ from .parsers import TextDocumentParser
 
 class ConsumerDeclaration:
 
-    MATCHING_FILES = re.compile("^.*\.(txt|md)$")
+    MATCHING_FILES = re.compile("^.*\.(te?xt|md|csv)$")
 
     @classmethod
     def handle(cls, sender, **kwargs):