yetangitu/recoll
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

added "all in one" rclepub1 filter (no individual indexing of chapters)

Browse source
This commit is contained in:
Jean-Francois Dockes 2016-12-05 15:19:02 +01:00
parent ee15caa509
commit 6670b36bb7
2 changed files with 107 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
src/Makefile.am
View file

@ -581,6 +581,7 @@ filters/rcldjvu.py \
filters/rcldoc.py \ filters/rcldoc.py \
filters/rcldvi \ filters/rcldvi \
filters/rclepub \ filters/rclepub \
filters/rclepub1 \
filters/rclexec1.py \ filters/rclexec1.py \
filters/rclexecm.py \ filters/rclexecm.py \
filters/rclfb2 \ filters/rclfb2 \

106
src/filters/rclepub1 Executable file
View file

@ -0,0 +1,106 @@
#!/usr/bin/env python
"""Extract Html content from an EPUB file (.chm), concatenating all sections"""
from __future__ import print_function
import sys
import os
import re
import rclexecm
try:
import epub
except:
print("RECFILTERROR HELPERNOTFOUND python:epub")
sys.exit(1);
class rclEPUB:
"""RclExecM slave worker for extracting all text from an EPUB
file. This version concatenates all nodes."""
def __init__(self, em):
self.em = em
self.em.setmimetype("text/html")
self.currentindex = 0
def _header(self):
meta = self.book.opf.metadata
title = ""
for tt, lang in meta.titles:
title += tt + " "
author = ""
for name, role, fileas in meta.creators:
author += name + " "
data = "<html>\n<head>\n"
if title:
data += "<title>" + self.em.htmlescape(title) + "</title>\n"
if author:
data += '<meta name="author" content="' + \
self.em.htmlescape(author).strip() + '">\n'
if meta.description:
data += '<meta name="description" content="' + \
self.em.htmlescape(meta.description) + '">\n'
data += "</head><body>"
data = data.encode('UTF-8')
return data
def extractone(self, params):
"""Extract EPUB data as concatenated HTML"""
ok = True
data = self._header()
ids = []
if self.book.opf.spine:
for id, linear in self.book.opf.spine.itemrefs:
ids.append(id)
else:
for id, item in self.book.opf.manifest.items():
ids.append(id)
for id in ids:
item = self.book.get_item(id)
if item is None or item.media_type != 'application/xhtml+xml':
continue
doc = self.book.read_item(item)
doc = re.sub(b'''<\?.*\?>''', b'', doc)
doc = re.sub(b'''<[hH][tT][mM][lL].*<[bB][oO][dD][yY][^>]*>''',
b'', doc, 1, re.DOTALL)
doc = re.sub(b'''</[bB][oO][dD][yY]>''', b'', doc)
doc = re.sub(b'''</[hH][tT][mM][lL]>''', b'', doc)
data += doc
data += b'</body></html>'
if ok:
return (ok, data, "", rclexecm.RclExecM.eofnext)
else:
return (ok, "", "", rclexecm.RclExecM.eofnow)
def openfile(self, params):
"""Open the EPUB file"""
self.currentindex = 0
if not "filename:" in params:
self.em.rclog("openfile: no file name")
return (ok, "", "", rclexecm.RclExecM.eofnow)
try:
self.book = epub.open_epub(params["filename:"].decode('UTF-8'))
except Exception as err:
self.em.rclog("openfile: epub.open failed: [%s]" % err)
return False
return True
def getipath(self, params):
return self.extractone(params)
def getnext(self, params):
if self.currentindex >= 1:
return (False, "", "", rclexecm.RclExecM.eofnow)
else:
ret= self.extractone(params)
self.currentindex += 1
return ret
proto = rclexecm.RclExecM()
extract = rclEPUB(proto)
rclexecm.main(proto, extract)