| """Plain-content document import/export. Layout, tracked changes and media are not preserved.""" |
| from pathlib import Path |
| import subprocess,tempfile,zipfile,xml.etree.ElementTree as ET,re |
| from xml.sax.saxutils import escape |
| W='{http://schemas.openxmlformats.org/wordprocessingml/2006/main}' |
| def read(path): |
| path=Path(path);ext=path.suffix.lower() |
| if ext=='.txt':return path.read_text(encoding='utf-8-sig') |
| if ext=='.rtf':return subprocess.check_output(['/usr/bin/textutil','-convert','txt','-stdout',str(path)]).decode('utf-8') |
| if ext=='.docx': |
| with zipfile.ZipFile(path) as z: |
| if sum(i.file_size for i in z.infolist())>100_000_000:raise ValueError('Document expands beyond the 100 MB import limit.') |
| root=ET.fromstring(z.read('word/document.xml')) |
| return '\n'.join(''.join(n.text or '' if n.tag==W+'t' else '\t' if n.tag==W+'tab' else '\n' if n.tag in (W+'br',W+'cr') else '' for n in p.iter()) for p in root.iter(W+'p')) |
| raise ValueError('Choose .txt, .rtf or .docx.') |
| def write(path,text): |
| path=Path(path);ext=path.suffix.lower() |
| if ext=='.txt':path.write_text(text,encoding='utf-8');return |
| if ext=='.rtf': |
| with tempfile.TemporaryDirectory() as d: |
| src=Path(d)/'content.txt';src.write_text(text,encoding='utf-8') |
| subprocess.run(['/usr/bin/textutil','-convert','rtf','-output',str(path),str(src)],check=True,capture_output=True) |
| return |
| if ext!='.docx':raise ValueError('Choose a .txt, .rtf or .docx filename.') |
| body=''.join('<w:p><w:r><w:t xml:space="preserve">'+escape(line)+'</w:t></w:r></w:p>' for line in text.splitlines()) |
| with zipfile.ZipFile(path,'w',zipfile.ZIP_DEFLATED) as z: |
| z.writestr('[Content_Types].xml','<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types"><Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/><Default Extension="xml" ContentType="application/xml"/><Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/></Types>') |
| z.writestr('_rels/.rels','<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/></Relationships>') |
| z.writestr('word/document.xml','<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:body>'+body+'<w:sectPr/></w:body></w:document>') |
| def spans(text,limit=700): |
| out=[] |
| for m in re.finditer(r'\S[\s\S]*?(?=\r?\n[^\S\r\n]*\r?\n|\Z)',text): |
| start,end=m.span() |
| while end>start and text[end-1].isspace():end-=1 |
| while end-start>limit: |
| part=text[start:start+limit] |
| sentences=list(re.finditer(r'[.!?؟。！？]["”’]*?(?=\s)',part)) |
| sentence_cuts=[m.end() for m in sentences if m.end()>=limit//3] |
| spaces=list(re.finditer(r'\s+',part)) |
| cut=sentence_cuts[-1] if sentence_cuts else spaces[-1].start() if spaces else limit |
| if cut<limit//3:cut=limit |
| stop=start+cut |
| while stop>start and text[stop-1].isspace():stop-=1 |
| out.append((start,stop));start=stop |
| while start<end and text[start].isspace():start+=1 |
| if start<end:out.append((start,end)) |
| return out |
|
|
| def assemble(text,locations,records): |
| out=[];cursor=0 |
| for i,(a,b) in enumerate(locations):out.extend((text[cursor:a],records.get(str(i),{}).get('text',text[a:b])));cursor=b |
| return ''.join(out)+text[cursor:] |
|
|
|
|
| def validate_spans(text,locations): |
| """Validate saved coverage without resegmenting checkpoints from older releases.""" |
| cursor=0 |
| if not isinstance(locations,list):raise ValueError('Invalid saved passage layout.') |
| for pair in locations: |
| if not isinstance(pair,(list,tuple)) or len(pair)!=2:raise ValueError('Invalid saved passage offsets.') |
| a,b=pair |
| if type(a) is not int or type(b) is not int or not cursor<=a<b<=len(text) or text[cursor:a].strip():raise ValueError('Invalid saved passage coverage.') |
| cursor=b |
| if text[cursor:].strip():raise ValueError('Saved passage layout omits text.') |
| return locations |
|
|
|
|
| def rewrite_allowance(text,locations,records,index,multiplier=2): |
| """Carry unused 2x character allowance forward within the original paragraph. |
| |
| Unprocessed earlier chunks reserve their original text length. Whitespace |
| between chunks stays in the assembled output and counts against the cap. |
| No allowance crosses a blank-line paragraph separator. |
| """ |
| first=index |
| while first>0: |
| gap=text[locations[first-1][1]:locations[first][0]] |
| if re.search(r'\r?\n[^\S\r\n]*\r?\n',gap):break |
| first-=1 |
| start=locations[first][0];end=locations[index][1] |
| used=0 |
| for j in range(first,index): |
| a,b=locations[j] |
| used+=len(records.get(str(j),{}).get('text',text[a:b])) |
| used+=locations[j+1][0]-b |
| return max(0,int(multiplier*(end-start))-used) |
|
|
