Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Remove invalid ASCII characters from plain text files

Browse Source
This commit is contained in:
Sengian 2010-07-31 13:15:47 +02:00
parent a80c304fa4
commit 3405615e54
2 changed files with 17 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/calibre/ebooks/txt/input.py
View File

@ -57,6 +57,7 @@ class TXTInput(InputFormatPlugin):
txt = preserve_spaces(txt) txt = preserve_spaces(txt)
txt = _ent_pat.sub(xml_entity_to_unicode, txt) txt = _ent_pat.sub(xml_entity_to_unicode, txt)
txt = txt.encode('utf-8')
if options.markdown: if options.markdown:
log.debug('Running text though markdown conversion...') log.debug('Running text though markdown conversion...')
@ -79,7 +80,7 @@ class TXTInput(InputFormatPlugin):
base = os.path.dirname(stream.name) base = os.path.dirname(stream.name)
htmlfile = open(os.path.join(base, 'temp_calibre_txt_input_to_html.html'), htmlfile = open(os.path.join(base, 'temp_calibre_txt_input_to_html.html'),
'wb') 'wb')
htmlfile.write(html.encode('utf-8')) htmlfile.write(html) #html.encode('utf-8')
htmlfile.close() htmlfile.close()
cwd = os.getcwdu() cwd = os.getcwdu()
odi = options.debug_pipeline odi = options.debug_pipeline

25
src/calibre/ebooks/txt/processor.py
View File

@ -19,7 +19,7 @@ HTML_TEMPLATE = u'<html><head><meta http-equiv="Content-Type" content="text/html
def convert_basic(txt, title='', epub_split_size_kb=0): def convert_basic(txt, title='', epub_split_size_kb=0):
# Strip whitespace from the beginning and end of the line. Also replace # Strip whitespace from the beginning and end of the line. Also replace
# all line breaks with \n. # all line breaks with \n.
txt = '\n'.join([line.strip() for line in txt.splitlines()]) txt = u'\n'.join([line.strip() for line in txt.splitlines()])
# Condense redundant spaces # Condense redundant spaces
txt = re.sub('[ ]{2,}', ' ', txt) txt = re.sub('[ ]{2,}', ' ', txt)
@ -29,23 +29,28 @@ def convert_basic(txt, title='', epub_split_size_kb=0):
txt = re.sub('(?<=.)\s+$', '', txt) txt = re.sub('(?<=.)\s+$', '', txt)
# Remove excessive line breaks. # Remove excessive line breaks.
txt = re.sub('\n{3,}', '\n\n', txt) txt = re.sub('\n{3,}', '\n\n', txt)
#remove ASCII invalid chars : 0 to 8 and 11-14 to 24
#illegal_char = re.compile('\x00|\x01|\x02|\x03|\x04|\x05|\x06|\x07|\x08| \
# \x0B|\x0E|\x0F|\x10|\x11|\x12|\x13|\x14|\x15|\x16|\x17|\x18')
txt = re.sub('\u000[0-8]|\u001[14-9]|\u002[0-4]', '', txt)
#Takes care if there is no point to split #Takes care if there is no point to split
if epub_split_size_kb > 0: if epub_split_size_kb > 0:
length_byte = len(txt.encode('utf-8')) length_byte = len(txt)
#Calculating the average chunk value for easy splitting as EPUB (+2 as a safe margin) #Calculating the average chunk value for easy splitting as EPUB (+2 as a safe margin)
chunk_size = long(length_byte / (int(length_byte / (epub_split_size_kb * 1024) ) + 2 )) chunk_size = long(length_byte / (int(length_byte / (epub_split_size_kb * 1024) ) + 2 ))
#if there are chunks with a superior size then go and break #if there are chunks with a superior size then go and break
if (len(filter(lambda x: len(x.encode('utf-8')) > chunk_size, txt.split('\n\n')))) : if (len(filter(lambda x: len(x) > chunk_size, txt.split('\n\n')))) :
txt = u'\n\n'.join([split_string_separator(line, chunk_size) for line in txt.split('\n\n')]) txt = u'\n\n'.join([split_string_separator(line, chunk_size)
for line in txt.split('\n\n')])
lines = [] lines = []
# Split into paragraphs based on having a blank line between text. # Split into paragraphs based on having a blank line between text.
for line in txt.split('\n\n'): for line in txt.split('\n\n'):
if line.strip(): if line.strip():
lines.append('<p>%s</p>' % prepare_string_for_xml(line.replace('\n', ' '))) lines.append(u'<p>%s</p>' % prepare_string_for_xml(line.replace('\n', ' ')))
return HTML_TEMPLATE % (title, '\n'.join(lines)) return HTML_TEMPLATE % (title, u'\n'.join(lines))
def convert_markdown(txt, title='', disable_toc=False): def convert_markdown(txt, title='', disable_toc=False):
md = markdown.Markdown( md = markdown.Markdown(
@ -57,11 +62,11 @@ def convert_markdown(txt, title='', disable_toc=False):
def separate_paragraphs_single_line(txt): def separate_paragraphs_single_line(txt):
txt = txt.replace('\r\n', '\n') txt = txt.replace('\r\n', '\n')
txt = txt.replace('\r', '\n') txt = txt.replace('\r', '\n')
txt = re.sub(u'(?<=.)\n(?=.)', u'\n\n', txt) txt = re.sub(u'(?<=.)\n(?=.)', '\n\n', txt)
return txt return txt
def separate_paragraphs_print_formatted(txt): def separate_paragraphs_print_formatted(txt):
txt = re.sub('(?miu)^(\t+|[ ]{2,})(?=.)', '\n\t', txt) txt = re.sub(u'(?miu)^(\t+|[ ]{2,})(?=.)', '\n\t', txt)
return txt return txt
def preserve_spaces(txt): def preserve_spaces(txt):
@ -77,9 +82,9 @@ def opf_writer(path, opf_name, manifest, spine, mi):
opf.render(opffile) opf.render(opffile)
def split_string_separator(txt, size) : def split_string_separator(txt, size) :
if len(txt.encode('utf-8')) > size: if len(txt) > size:
txt = u''.join([re.sub(u'\.(?P<ends>[^.]*)$', u'.\n\n\g<ends>', txt = u''.join([re.sub(u'\.(?P<ends>[^.]*)$', u'.\n\n\g<ends>',
txt[i:i+size], 1) for i in txt[i:i+size], 1) for i in
xrange(0, len(txt.encode('utf-8')), size)]) xrange(0, len(txt), size)])
return txt return txt