office meta plugin

.index.yaml

@@ -0,0 +1,150 @@
+contexts:
+  Chripo McFlu:
+  - ./test/chirpy.wav
+  'calc #tessssting':
+  - ./test/sheet.xlsx
+  - ./test/table.ods
+  'concon #tagz':
+  - ./test/word.docx
+  erfwegf:
+  - ./COMMANDS.md
+  frrreee:
+  - ./README.md
+  python:
+  - ./orvani/plugins/hashdoubleslash.py
+  - ./TODO.md
+  test:
+  - ./test/test.txt
+  this:
+  - ./test/office.odt
+  watch:
+  - ./test/chirpy.wav
+files:
+  ./COMMANDS.md:
+    contexts:
+    - erfwegf
+    note: This is awesome
+    projects:
+    - coding
+    tags:
+    - super
+    - great
+  ./README.md:
+    contexts:
+    - frrreee
+    projects:
+    - test2
+    - test
+  ./TODO.md:
+    contexts:
+    - python
+    note: Chawera
+    projects:
+    - bokertov
+    tags:
+    - frrr
+    - rusty
+  ./orvani/plugins/hashdoubleslash.py:
+    contexts:
+    - python
+    note: It even works in Python code
+    projects:
+    - orvani
+    tags:
+    - example
+  ./test/chirpy.wav:
+    contexts:
+    - watch
+    - Chripo McFlu
+    note:
+    - This is a title
+    projects:
+    - parakeetio
+    - sensorwatch
+    tags:
+    - funk
+  ./test/office.odt:
+    contexts:
+    - this
+    note: and a note
+    projects:
+    - oopsie
+    tags:
+    - whoa
+    - that
+  ./test/sheet.xlsx:
+    contexts:
+    - 'calc #tessssting'
+    projects: []
+    tags: []
+  ./test/table.ods:
+    contexts:
+    - 'calc #tessssting'
+    projects: []
+    tags: []
+  ./test/test.txt:
+    contexts:
+    - test
+    note: frrr
+    projects:
+    - test
+    tags:
+    - faa
+    - test
+  ./test/word.docx:
+    contexts:
+    - 'concon #tagz'
+    projects: []
+    tags: []
+note:
+  Chawera:
+  - ./TODO.md
+  It even works in Python code:
+  - ./orvani/plugins/hashdoubleslash.py
+  This is a title:
+  - ./test/chirpy.wav
+  This is awesome:
+  - ./COMMANDS.md
+  and a note:
+  - ./test/office.odt
+  frrr:
+  - ./test/test.txt
+projects:
+  bokertov:
+  - ./TODO.md
+  coding:
+  - ./COMMANDS.md
+  oopsie:
+  - ./test/office.odt
+  orvani:
+  - ./orvani/plugins/hashdoubleslash.py
+  parakeetio:
+  - ./test/chirpy.wav
+  sensorwatch:
+  - ./test/chirpy.wav
+  test:
+  - ./test/test.txt
+  - ./README.md
+  test2:
+  - ./README.md
+tags:
+  example:
+  - ./orvani/plugins/hashdoubleslash.py
+  faa:
+  - ./test/test.txt
+  frrr:
+  - ./TODO.md
+  funk:
+  - ./test/chirpy.wav
+  great:
+  - ./COMMANDS.md
+  rusty:
+  - ./TODO.md
+  super:
+  - ./COMMANDS.md
+  test:
+  - ./test/test.txt
+  that:
+  - ./test/office.odt
+  whoa:
+  - ./test/office.odt

metareaders.py

@@ -1,26 +0,0 @@
-import taglib
-
-with taglib.File("/home/flux/Documents/230605-191750.wav", save_on_exit=True) as song:
-
-import frontmatter
-
-with open('README.md', 'r') as data:
-    y = frontmatter.load(data)
-
-print(y.metadata)
-
-@orvani.metareader
-    def yaml_read(conf, db):
-        for (root,dirs,files) in os.walk(path):
-            if files:
-                for file in files:
-                            rpath = os.path.join(root, dir)
-            f, ext = os.path.splitext(file)
-            if ext[1:] in conf['index'] and ext[1:] in ['md', 'txt']:
-                with open(file, 'r') as data:
-                    y = frontmatter.load(data)
-                    print(y)
-                    if y.metadata:
-                        for meta in y.metadata:
-                            db[file][meta] = y.metadata[meta]
-        return db

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
+from plugins import frontmatter, hashdoubleslash, id3, office
 
 def mktable(query: str, index: dict):
     console = Console()
@@ -89,6 +89,7 @@ def main():
         frontmatter.reader(o)
         hashdoubleslash.reader(o)
         id3.reader(o)
+        office.reader(o)
 
     # orvani.metadata()
 

orvani/plugins/office.py

@@ -0,0 +1,82 @@
+import re
+import mimetypes
+import shutil
+from pathlib import Path
+from olefile import OleFileIO
+
+NAME = 'office'
+TYPES = ['.doc', '.xls', '.ppt', '.docx', '.xlsx', '.pptx', '.odt', '.ods', '.odp']
+RE_ODT_CTX = r"<meta:keyword>((.*))<\/meta:keyword>"
+RE_ODT_NOTE = r"<dc:description>((.*))<\/dc:description>"
+
+# Office Document processing inspired by
+# https://github.com/kappapiana/anonymize/blob/master/anonymize.py
+
+def unzip_file(orig_file, tmp_dir):
+    type = mimetypes.guess_type(orig_file)
+    filetype = {
+        "application/vnd.oasis.opendocument.text" : "odt",
+        "application/vnd.oasis.opendocument.spreadsheet" : "ods",
+        "application/vnd.oasis.opendocument.presentation" : "odp",
+        "application/vnd.openxmlformats-officedocument.wordprocessingml.document" : "docx",
+        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" : "xlsx",
+        "application/vnd.openxmlformats-officedocument.presentationml.presentation" : "pptx",
+    }
+    if type[0] in filetype:
+        shutil.unpack_archive(orig_file, tmp_dir, 'zip')
+        return filetype[type[0]]
+    else:
+        return type[0]
+
+def reader(o):
+    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:
+        tmp_folder = Path('unzip__' + file.stem)
+        file_type = unzip_file(o.path, tmp_folder)
+        tags = note = []
+        # OpenOffice / LibreOffice / Open Document Format
+        if file_type in ['odt', 'ods', 'odp']:
+            meta_file = tmp_folder / 'meta.xml'
+            meta_content = meta_file.read_text()
+            tagsearch = re.findall(RE_ODT_CTX, meta_content)
+            if tagsearch:
+                tags = list(set(tagsearch[0]))
+            notesearch = re.findall(RE_ODT_NOTE, meta_content)
+            if notesearch:
+                note = list(set(notesearch[0]))
+            argv = [x for x in ' '.join(tags).split(' ') + note if x != '']
+            context = o.context(argv)
+            for context_key in context.keys():
+                o.update(o.path, context, context_key)
+            shutil.rmtree(tmp_folder)
+        # Microsoft Office Format
+        elif file_type in ['docx', 'xlsx', 'pptx']:
+            meta_file = tmp_folder / 'docProps' / 'core.xml'
+            meta_content = meta_file.read_text()
+            tagsearch = re.findall(RE_ODT_CTX, meta_content)
+            if tagsearch:
+                tags = list(set(tagsearch[0]))
+            notesearch = re.findall(RE_ODT_NOTE, meta_content)
+            if notesearch:
+                note = list(set(notesearch[0]))
+            argv = [x for x in ' '.join(tags).split(' ') + note if x != '']
+            context = o.context(argv)
+            for context_key in context.keys():
+                o.update(o.path, context, context_key)
+            shutil.rmtree(tmp_folder)
+        elif file_type in ['application/msword', 'application/vnd.ms-excel', 'application/vnd.ms-powerpoint']:
+            ole = OleFileIO(o.path)
+            meta = ole.get_metadata()
+            ole.close()
+            if meta.keywords:
+                tags = meta.keywords.decode('UTF-8').split(' ')
+            if meta.comments:
+                note = [meta.comments.decode('UTF-8')]
+            argv = [x for x in tags + note if x != '']
+            context = o.context(argv)
+            for context_key in context.keys():
+                o.update(o.path, context, context_key)

requirements.txt

@@ -1,2 +1,4 @@
+olefile==0.46
+pytaglib==2.0.0
 PyYAML==6.0
 rich==13.4.1