bugfixes
This commit is contained in:
randogoth
parent
d76fac352f
commit
d1b829f647
11 changed files with 94 additions and 41 deletions
|
|
@ -152,5 +152,11 @@ def main():
|
|||
if args.file and args.context:
|
||||
orvani.write(args.context[0], args.file)
|
||||
|
||||
elif args.command in ['export']:
|
||||
orvani.export(args.file)
|
||||
|
||||
elif args.command in ['import']:
|
||||
orvani.load(args.file)
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
|
|
|
|||
|
|
@ -1,4 +1,5 @@
|
|||
import os
|
||||
import re
|
||||
import yaml
|
||||
import shutil
|
||||
from pathlib import Path
|
||||
|
|
@ -37,6 +38,7 @@ class OrvaniTag:
|
|||
CTX = {}
|
||||
ENABLE_PLUGINS = True
|
||||
PLUGINS = []
|
||||
REGEX = r'\s*([@+]\w+|#\w+)'
|
||||
|
||||
def __init__(self, path: str=CONTEXT_FILE, cache: str=CACHE_FILE, contexts=CONTEXTS, plugins:list=DEFAULT_PLUGINS):
|
||||
"""
|
||||
|
|
@ -121,7 +123,7 @@ class OrvaniTag:
|
|||
for context_key in self.CTX.keys():
|
||||
if self.CTX[context_key] != None:
|
||||
context.update( { context_key : []})
|
||||
for arg in argv:
|
||||
for arg in [x for x in argv if len(x) > 0]:
|
||||
arg.replace(',', '')
|
||||
for context_key in self.CTX.keys():
|
||||
if str(arg)[0] in self.CTX.values():
|
||||
|
|
@ -427,12 +429,20 @@ class OrvaniTag:
|
|||
self.PLUGINS.append(function)
|
||||
return function
|
||||
|
||||
def get_argv(self, context_string: str):
|
||||
tags = re.findall(self.REGEX, context_string)
|
||||
note = re.sub(self.REGEX, '', context_string).lstrip()
|
||||
argv = ' '.join(tags).split(' ') + [note]
|
||||
argv = [x for x in list(set(argv)) if x != '']
|
||||
return argv
|
||||
|
||||
def __metadata(self, filename: str):
|
||||
obj = {
|
||||
'file' : Path(),
|
||||
'config' : self.CONFIG,
|
||||
'schema' : self.CTX,
|
||||
'context' : self.__context,
|
||||
'string' : self.get_argv
|
||||
}
|
||||
o = SimpleNamespace(**obj)
|
||||
for plugin_name in self.PLUGINS:
|
||||
|
|
@ -457,7 +467,7 @@ class OrvaniTag:
|
|||
context_keys = list(CONTEXTS.keys())
|
||||
for context_key in context_keys:
|
||||
if not context_key in context:
|
||||
context[context_key] = None
|
||||
context[context_key] = ''
|
||||
if context[context_key]:
|
||||
if CONTEXTS[context_key]:
|
||||
prefix = CONTEXTS[context_key]
|
||||
|
|
@ -467,8 +477,6 @@ class OrvaniTag:
|
|||
elements.append(' '.join([prefix + tag for tag in context[context_key]]))
|
||||
else:
|
||||
elements.append(context[context_key])
|
||||
else:
|
||||
elements.append(None)
|
||||
return elements
|
||||
|
||||
def write(self, filename: str, method: str):
|
||||
|
|
@ -477,7 +485,8 @@ class OrvaniTag:
|
|||
'config' : self.CONFIG,
|
||||
'schema' : self.CTX,
|
||||
'context' : {},
|
||||
'collect' : self.__collect_contexts
|
||||
'collect' : self.__collect_contexts,
|
||||
'string' : self.get_argv
|
||||
}
|
||||
o = SimpleNamespace(**obj)
|
||||
for plugin_name in self.PLUGINS:
|
||||
|
|
@ -500,3 +509,23 @@ class OrvaniTag:
|
|||
if hasattr(plugin, 'writer'):
|
||||
plugin.writer(o)
|
||||
|
||||
def export(self, filename:str):
|
||||
if filename == '' or filename == None:
|
||||
filename = 'context.txt'
|
||||
file = Path(filename)
|
||||
index = self.list(file.parent, False, False, True, False, False, '')
|
||||
items = index['index']['items']
|
||||
content = ""
|
||||
for path in items:
|
||||
string = ' '.join([x for x in self.__collect_contexts(items[path]) if x != None])
|
||||
content += f'{path} --- {string}\n'
|
||||
file.write_text(content)
|
||||
|
||||
def load(self, filename:str):
|
||||
if filename == '' or filename == None:
|
||||
filename = 'context.txt'
|
||||
file = Path(filename)
|
||||
imported = file.read_text()
|
||||
known = self.list(file.parent, False, False, True, False, False, '')['index']['items']
|
||||
print(known)
|
||||
|
||||
|
|
|
|||
|
|
@ -37,19 +37,20 @@ def reader(o):
|
|||
if line_num > 5:
|
||||
break
|
||||
if line.strip().startswith("#// "):
|
||||
tags = re.findall(REGEX, line.strip()[3:])
|
||||
note = re.sub(REGEX, '', line.strip()[3:]).lstrip()
|
||||
argv = ' '.join(tags).split(' ') + [note]
|
||||
argv = o.string(line.strip()[3:])
|
||||
context = o.context(argv)
|
||||
return context
|
||||
|
||||
def writer(o):
|
||||
string = PREFIX + ' '.join([x for x in o.collect(o.context) if x != None]) + '\n'
|
||||
string = PREFIX + ' '.join(o.collect(o.context)) + '\n'
|
||||
with o.file.open() as data:
|
||||
content = data.readlines()
|
||||
for num, line in enumerate(content):
|
||||
if line.strip().startswith("#// ") or num > 3:
|
||||
break
|
||||
num = 0
|
||||
line = ''
|
||||
if len(content):
|
||||
for num, line in enumerate(content):
|
||||
if line.strip().startswith("#// ") or num > 3:
|
||||
break
|
||||
if not num > 3 and line.strip().startswith("#// "):
|
||||
content[num] = string
|
||||
with o.file.open('w') as file:
|
||||
|
|
|
|||
|
|
@ -23,10 +23,7 @@ def reader(o):
|
|||
id3map[context_key] = metadata[ctag]
|
||||
if 'COMMENT' in metadata:
|
||||
comment = metadata['COMMENT']
|
||||
tags = re.findall(REGEX, comment[0].strip())
|
||||
note = re.sub(REGEX, '', comment[0].strip()).lstrip()
|
||||
argv = ' '.join(tags).split(' ') + [note]
|
||||
argv = [x for x in argv if x != '']
|
||||
argv = o.string(comment[0].strip())
|
||||
context = o.context(argv)
|
||||
if not universal in context:
|
||||
context[universal] = []
|
||||
|
|
@ -39,6 +36,6 @@ def reader(o):
|
|||
return context
|
||||
|
||||
def writer(o):
|
||||
string = ' '.join([x for x in o.collect(o.context) if x != None])
|
||||
string = ' '.join(o.collect(o.context))
|
||||
with taglib.File(o.file, save_on_exit=True) as song:
|
||||
song.tags['COMMENT'] = [string]
|
||||
|
|
@ -7,9 +7,8 @@ from olefile import OleFileIO
|
|||
|
||||
NAME = 'office'
|
||||
TYPES = ['.doc', '.xls', '.ppt', '.docx', '.xlsx', '.pptx', '.odt', '.ods', '.odp']
|
||||
RE_ODT_CTX = r"(?P<pre><meta:keyword>)(?P<body>.*?)(?P<post><\/meta:keyword>)"
|
||||
RE_DOCX_CTX = r"(?P<pre><cp:keywords>)(?P<body>.*?)(?P<post><\/cp:keywords>)"
|
||||
REGEX = r"(?P<pre><dc:description>)(?P<body>.*?)(?P<post><\/dc:description>)"
|
||||
XML_REGEX = r"(?P<pre><dc:description>)(?P<body>.*?)(?P<post><\/dc:description>)"
|
||||
REGEX = r'\s*([@+]\w+|#\w+)'
|
||||
|
||||
# Office Document processing inspired by
|
||||
# https://github.com/kappapiana/anonymize/blob/master/anonymize.py
|
||||
|
|
@ -30,16 +29,12 @@ def unzip_file(orig_file, tmp_dir):
|
|||
else:
|
||||
return type[0]
|
||||
|
||||
def get_context(meta_file, re_ctx):
|
||||
tags = note = []
|
||||
def get_context_string(meta_file):
|
||||
ctx = ''
|
||||
meta_content = meta_file.read_text()
|
||||
tagsearch = re.search(re_ctx, meta_content)
|
||||
if tagsearch:
|
||||
tags = tagsearch.group('body').split(' ')
|
||||
notesearch = re.search(REGEX, meta_content)
|
||||
if notesearch:
|
||||
note = [notesearch.group('body')]
|
||||
return [x for x in ' '.join(tags).split(' ') + note if x != '']
|
||||
csearch = re.search(XML_REGEX, meta_content)
|
||||
if csearch:
|
||||
return csearch.group('body')
|
||||
|
||||
|
||||
def reader(o):
|
||||
|
|
@ -50,7 +45,7 @@ def reader(o):
|
|||
# OpenOffice / LibreOffice / Open Document Format
|
||||
if file_type in ['odt', 'ods', 'odp']:
|
||||
meta_file = tmp_folder / 'meta.xml'
|
||||
argv = get_context(meta_file, RE_ODT_CTX)
|
||||
argv = o.string(get_context_string(meta_file))
|
||||
context = o.context(argv)
|
||||
shutil.rmtree(tmp_folder)
|
||||
return context
|
||||
|
|
@ -58,7 +53,7 @@ def reader(o):
|
|||
# Microsoft Office Format
|
||||
elif file_type in ['docx', 'xlsx', 'pptx']:
|
||||
meta_file = tmp_folder / 'docProps' / 'core.xml'
|
||||
argv = get_context(meta_file, RE_DOCX_CTX)
|
||||
argv = o.string(get_context_string(meta_file))
|
||||
context = o.context(argv)
|
||||
shutil.rmtree(tmp_folder)
|
||||
return context
|
||||
|
|
@ -68,20 +63,17 @@ def reader(o):
|
|||
ole = OleFileIO(o.file)
|
||||
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)
|
||||
return context
|
||||
argv = o.string(meta.comments.decode('UTF-8'))
|
||||
context = o.context(argv)
|
||||
return context
|
||||
|
||||
|
||||
def writer(o):
|
||||
string = ' '.join([x for x in o.collect(o.context) if x != None])
|
||||
string = ' '.join(o.collect(o.context))
|
||||
tmp_folder = Path('unzip__' + o.file.stem)
|
||||
file_type = unzip_file(o.file, tmp_folder)
|
||||
regex = re.compile(REGEX)
|
||||
regex = re.compile(XML_REGEX)
|
||||
string = f"\\g<pre>{string}\\g<post>"
|
||||
|
||||
# OpenOffice / LibreOffice / Open Document Format
|
||||
|
|
|
|||
|
|
@ -18,7 +18,7 @@ def reader(o):
|
|||
return context
|
||||
|
||||
def writer(o):
|
||||
string = ' '.join([x for x in o.collect(o.context) if x != None])
|
||||
string = ' '.join(o.collect(o.context))
|
||||
pdf = PdfReader(o.file)
|
||||
pdf.Info.Keywords = string
|
||||
PdfWriter(o.file, trailer=pdf).write()
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue