pdf plugin

orvani/cmd.py

@@ -5,7 +5,7 @@ from pathlib import Path
 from rich.console import Console
 from rich.table import Table
 from orvani import OrvaniTag, CONTEXT_FILE, CACHE_FILE, CONTEXTS
-from plugins import frontmatter, hashdoubleslash, id3, office
+from plugins import frontmatter, hashdoubleslash, id3, office, pdf
 
 def mktable(query: str, index: dict, filter=None):
     console = Console()
@@ -98,6 +98,7 @@ def main():
         hashdoubleslash.reader(o)
         id3.reader(o)
         office.reader(o)
+        pdf.reader(o)
 
     orvani.PLUGINS = args.no_plugins
 

orvani/orvani.py

@@ -112,6 +112,7 @@ class OrvaniTag:
             if self.CTX[context_key] != None:
                 context.update( { context_key : []})
         for arg in argv:
+            arg.replace(',', '')
             for context_key in self.CTX.keys():
                 if str(arg)[0] in self.CTX.values():
                     # Schema with prefix

orvani/plugins/pdf.py

@@ -0,0 +1,28 @@
+import re
+import shutil
+from pathlib import Path
+from pdfrw import PdfReader, PdfWriter
+
+NAME = 'pdf'
+TYPES = ['.pdf']
+REGEX = r'\s*([@+]\w+|#\w+)'
+
+def reader(o):
+    if 'plugins' in o.config:
+        if NAME not in o.config['plugins']:
+            return
+    file = Path(o.path)
+    suffixes = TYPES
+    if NAME in o.config:
+        if 'types' in o.config[NAME]:
+            suffixes = o.config[NAME]['types']
+    if file.suffix in suffixes:
+        pdf = PdfReader(o.path)
+        if pdf.Info.Keywords:
+            tags = re.findall(REGEX, pdf.Info.Keywords.strip())
+            note = re.sub(REGEX, '', pdf.Info.Keywords.strip()).replace('(', '').replace(',', '').replace(')', '').strip()
+            argv = ' '.join(tags).split(' ') + [note]
+            argv = [x for x in argv if x != '']
+            context = o.context(argv)
+            for context_key in context.keys():
+                o.update(o.path, context, context_key)