Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

pep8

Browse Source
This commit is contained in:
Kovid Goyal 2014-07-19 00:55:15 +05:30
parent c052186b18
commit 49b0726efa
1 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
src/calibre/ebooks/conversion/preprocess.py
View File

@ -148,20 +148,20 @@ class DocAnalysis(object):
maxLineLength=1900 # Discard larger than this to stay in range maxLineLength=1900 # Discard larger than this to stay in range
buckets=20 # Each line is divided into a bucket based on length buckets=20 # Each line is divided into a bucket based on length
#print "there are "+str(len(lines))+" lines" # print "there are "+str(len(lines))+" lines"
#max = 0 # max = 0
#for line in self.lines: # for line in self.lines:
# l = len(line) # l = len(line)
# if l > max: # if l > max:
# max = l # max = l
#print "max line found is "+str(max) # print "max line found is "+str(max)
# Build the line length histogram # Build the line length histogram
hRaw = [0 for i in range(0,buckets)] hRaw = [0 for i in range(0,buckets)]
for line in self.lines: for line in self.lines:
l = len(line) l = len(line)
if l > minLineLength and l < maxLineLength: if l > minLineLength and l < maxLineLength:
l = int(l/100) l = int(l/100)
#print "adding "+str(l) # print "adding "+str(l)
hRaw[l]+=1 hRaw[l]+=1
# Normalize the histogram into percents # Normalize the histogram into percents
@ -170,8 +170,8 @@ class DocAnalysis(object):
h = [float(count)/totalLines for count in hRaw] h = [float(count)/totalLines for count in hRaw]
else: else:
h = [] h = []
#print "\nhRaw histogram lengths are: "+str(hRaw) # print "\nhRaw histogram lengths are: "+str(hRaw)
#print " percents are: "+str(h)+"\n" # print " percents are: "+str(h)+"\n"
# Find the biggest bucket # Find the biggest bucket
maxValue = 0 maxValue = 0
@ -180,10 +180,10 @@ class DocAnalysis(object):
maxValue = h[i] maxValue = h[i]
if maxValue < percent: if maxValue < percent:
#print "Line lengths are too variable. Not unwrapping." # print "Line lengths are too variable. Not unwrapping."
return False return False
else: else:
#print str(maxValue)+" of the lines were in one bucket" # print str(maxValue)+" of the lines were in one bucket"
return True return True
class Dehyphenator(object): class Dehyphenator(object):
@ -577,7 +577,7 @@ class HTMLPreProcessor(object):
docanalysis = DocAnalysis('pdf', html) docanalysis = DocAnalysis('pdf', html)
length = docanalysis.line_length(getattr(self.extra_opts, 'unwrap_factor')) length = docanalysis.line_length(getattr(self.extra_opts, 'unwrap_factor'))
if length: if length:
#print "The pdf line length returned is " + str(length) # print "The pdf line length returned is " + str(length)
# unwrap em/en dashes # unwrap em/en dashes
end_rules.append((re.compile(u'(?<=.{%i}[–—])\s*<p>\s*(?=[[a-z\d])' % length), lambda match: '')) end_rules.append((re.compile(u'(?<=.{%i}[–—])\s*<p>\s*(?=[[a-z\d])' % length), lambda match: ''))
end_rules.append( end_rules.append(
@ -610,7 +610,7 @@ class HTMLPreProcessor(object):
with open(os.path.join(odir, name), 'wb') as f: with open(os.path.join(odir, name), 'wb') as f:
f.write(raw.encode('utf-8')) f.write(raw.encode('utf-8'))
#dump(html, 'pre-preprocess') # dump(html, 'pre-preprocess')
for rule in rules + end_rules: for rule in rules + end_rules:
try: try:
@ -636,7 +636,7 @@ class HTMLPreProcessor(object):
if pdf_markup.get_word_count(html) > 7000: if pdf_markup.get_word_count(html) > 7000:
html = pdf_markup.markup_chapters(html, totalwords, True) html = pdf_markup.markup_chapters(html, totalwords, True)
#dump(html, 'post-preprocess') # dump(html, 'post-preprocess')
# Handle broken XHTML w/ SVG (ugh) # Handle broken XHTML w/ SVG (ugh)
if 'svg:' in html and SVG_NS not in html: if 'svg:' in html and SVG_NS not in html: