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

cleanup.

Browse Source
This commit is contained in:
John Schember 2011-04-17 19:42:39 -04:00
parent c0cf0e91d4
commit 377313df7d
1 changed files with 16 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
src/calibre/ebooks/pdb/plucker/reader.py
View File

@ -183,6 +183,9 @@ class SectionHeaderText(object):
def __init__(self, section_header, raw): def __init__(self, section_header, raw):
# The uncompressed size of each paragraph. # The uncompressed size of each paragraph.
self.sizes = [] self.sizes = []
# uncompressed offset of each paragraph starting
# at the beginning of the PHTML.
self.paragraph_offsets = []
# Paragraph attributes. # Paragraph attributes.
self.attributes = [] self.attributes = []
@ -191,6 +194,11 @@ class SectionHeaderText(object):
self.sizes.append(struct.unpack('>H', raw[adv:2+adv])[0]) self.sizes.append(struct.unpack('>H', raw[adv:2+adv])[0])
self.attributes.append(struct.unpack('>H', raw[2+adv:4+adv])[0]) self.attributes.append(struct.unpack('>H', raw[2+adv:4+adv])[0])
running_offset = 0
for size in self.sizes:
running_offset += size
self.paragraph_offsets.append(running_offset)
class SectionMetadata(object): class SectionMetadata(object):
''' '''
@ -299,6 +307,7 @@ class Reader(FormatReader):
* UTF 16 and 32 characters. * UTF 16 and 32 characters.
* Margins. * Margins.
* Alignment. * Alignment.
* Font color.
* DATATYPE_MAILTO * DATATYPE_MAILTO
* DATATYPE_TABLE(_COMPRESSED) * DATATYPE_TABLE(_COMPRESSED)
* DATATYPE_EXT_ANCHOR_INDEX * DATATYPE_EXT_ANCHOR_INDEX
@ -381,13 +390,13 @@ class Reader(FormatReader):
html = u'<html><body>' html = u'<html><body>'
section_header, section_data = self.sections[num] section_header, section_data = self.sections[num]
if section_header.type == DATATYPE_PHTML: if section_header.type == DATATYPE_PHTML:
html += self.process_phtml(section_data.header, section_data.data) html += self.process_phtml(section_data.data, section_data.header.paragraph_offsets)
elif section_header.type == DATATYPE_PHTML_COMPRESSED: elif section_header.type == DATATYPE_PHTML_COMPRESSED:
d = self.decompress_phtml(section_data.data) d = self.decompress_phtml(section_data.data)
html += self.process_phtml(section_data.header, d).decode(self.get_text_uid_encoding(section_header.uid), 'replace') html += self.process_phtml(d, section_data.header.paragraph_offsets).decode(self.get_text_uid_encoding(section_header.uid), 'replace')
html += '</body></html>' html += '</body></html>'
htmlf.write(html.encode('utf-8')) htmlf.write(html.encode('utf-8'))
# Images. # Images.
# Cache the image sizes in case they are used by a composite image. # Cache the image sizes in case they are used by a composite image.
image_sizes = {} image_sizes = {}
@ -498,7 +507,7 @@ class Reader(FormatReader):
#from calibre.ebooks.compression.palmdoc import decompress_doc #from calibre.ebooks.compression.palmdoc import decompress_doc
return decompress_doc(data) return decompress_doc(data)
def process_phtml(self, sub_header, d): def process_phtml(self, d, paragraph_offsets=[]):
html = u'<p id="p0">' html = u'<p id="p0">'
offset = 0 offset = 0
paragraph_open = True paragraph_open = True
@ -506,11 +515,6 @@ class Reader(FormatReader):
need_set_p_id = False need_set_p_id = False
p_num = 1 p_num = 1
font_specifier_close = '' font_specifier_close = ''
paragraph_offsets = []
running_offset = 0
for size in sub_header.sizes:
running_offset += size
paragraph_offsets.append(running_offset)
while offset < len(d): while offset < len(d):
if not paragraph_open: if not paragraph_open:
@ -754,4 +758,7 @@ class Reader(FormatReader):
return html return html
def get_text_uid_encoding(self, uid): def get_text_uid_encoding(self, uid):
# Return the user sepcified input encoding,
# otherwise return the alternate encoding specified for the uid,
# otherwise retur the default encoding for the document.
return self.options.input_encoding if self.options.input_encoding else self.uid_text_secion_encoding.get(uid, self.default_encoding) return self.options.input_encoding if self.options.input_encoding else self.uid_text_secion_encoding.get(uid, self.default_encoding)