From 7343d48a37227ed8e9093e2ccf4aead31aac614d Mon Sep 17 00:00:00 2001 From: John Schember Date: Thu, 6 Jan 2011 20:04:11 -0500 Subject: [PATCH 1/4] Remove PDB and TCR input options. TXT auto options are default and should suffice. --- src/calibre/ebooks/fb2/fb2ml.py | 2 +- src/calibre/ebooks/pdb/input.py | 24 ------------------------ src/calibre/ebooks/tcr/input.py | 24 ------------------------ src/calibre/gui2/convert/pdb_input.py | 25 ------------------------- src/calibre/gui2/convert/tcr_input.py | 25 ------------------------- 5 files changed, 1 insertion(+), 99 deletions(-) delete mode 100644 src/calibre/gui2/convert/pdb_input.py delete mode 100644 src/calibre/gui2/convert/tcr_input.py diff --git a/src/calibre/ebooks/fb2/fb2ml.py b/src/calibre/ebooks/fb2/fb2ml.py index f6deab677a..4dd6e7c7ae 100644 --- a/src/calibre/ebooks/fb2/fb2ml.py +++ b/src/calibre/ebooks/fb2/fb2ml.py @@ -173,7 +173,7 @@ class FB2MLizer(object): if title_item.spine_position is None and title_item.media_type == 'application/xhtml+xml': self.oeb_book.spine.insert(0, title_item, True) # Create xhtml page to reference cover image so it can be used. - if self.oeb_book.metadata.cover and unicode(self.oeb_book.metadata.cover[0]) in self.oeb_book.manifest.ids: + if not title_name and self.oeb_book.metadata.cover and unicode(self.oeb_book.metadata.cover[0]) in self.oeb_book.manifest.ids: id = unicode(self.oeb_book.metadata.cover[0]) cover_item = self.oeb_book.manifest.ids[id] if cover_item.media_type in OEB_RASTER_IMAGES: diff --git a/src/calibre/ebooks/pdb/input.py b/src/calibre/ebooks/pdb/input.py index 3688abff3f..8c754782a2 100644 --- a/src/calibre/ebooks/pdb/input.py +++ b/src/calibre/ebooks/pdb/input.py @@ -18,30 +18,6 @@ class PDBInput(InputFormatPlugin): description = 'Convert PDB to HTML' file_types = set(['pdb']) - options = set([ - OptionRecommendation(name='paragraph_type', recommended_value='auto', - choices=['auto', 'block', 'single', 'print'], - help=_('Paragraph structure.\n' - 'choices are [\'auto\', \'block\', \'single\', \'print\', \'markdown\']\n' - '* auto: Try to auto detect paragraph type.\n' - '* block: Treat a blank line as a paragraph break.\n' - '* single: Assume every line is a paragraph.\n' - '* print: Assume every line starting with 2+ spaces or a tab ' - 'starts a paragraph.')), - OptionRecommendation(name='formatting_type', recommended_value='auto', - choices=['auto', 'none', 'markdown'], - help=_('Formatting used within the document.' - '* auto: Try to auto detect the document formatting.\n' - '* none: Do not modify the paragraph formatting. Everything is a paragraph.\n' - '* markdown: Run the input though the markdown pre-processor. ' - 'To learn more about markdown see')+' http://daringfireball.net/projects/markdown/'), - OptionRecommendation(name='preserve_spaces', recommended_value=False, - help=_('Normally extra spaces are condensed into a single space. ' - 'With this option all spaces will be displayed.')), - OptionRecommendation(name="markdown_disable_toc", recommended_value=False, - help=_('Do not insert a Table of Contents into the output text.')), - ]) - def convert(self, stream, options, file_ext, log, accelerators): header = PdbHeaderReader(stream) diff --git a/src/calibre/ebooks/tcr/input.py b/src/calibre/ebooks/tcr/input.py index c1dcef235d..4c759c5be2 100644 --- a/src/calibre/ebooks/tcr/input.py +++ b/src/calibre/ebooks/tcr/input.py @@ -16,30 +16,6 @@ class TCRInput(InputFormatPlugin): description = 'Convert TCR files to HTML' file_types = set(['tcr']) - options = set([ - OptionRecommendation(name='paragraph_type', recommended_value='auto', - choices=['auto', 'block', 'single', 'print'], - help=_('Paragraph structure.\n' - 'choices are [\'auto\', \'block\', \'single\', \'print\', \'markdown\']\n' - '* auto: Try to auto detect paragraph type.\n' - '* block: Treat a blank line as a paragraph break.\n' - '* single: Assume every line is a paragraph.\n' - '* print: Assume every line starting with 2+ spaces or a tab ' - 'starts a paragraph.')), - OptionRecommendation(name='formatting_type', recommended_value='auto', - choices=['auto', 'none', 'markdown'], - help=_('Formatting used within the document.' - '* auto: Try to auto detect the document formatting.\n' - '* none: Do not modify the paragraph formatting. Everything is a paragraph.\n' - '* markdown: Run the input though the markdown pre-processor. ' - 'To learn more about markdown see')+' http://daringfireball.net/projects/markdown/'), - OptionRecommendation(name='preserve_spaces', recommended_value=False, - help=_('Normally extra spaces are condensed into a single space. ' - 'With this option all spaces will be displayed.')), - OptionRecommendation(name="markdown_disable_toc", recommended_value=False, - help=_('Do not insert a Table of Contents into the output text.')), - ]) - def convert(self, stream, options, file_ext, log, accelerators): log.info('Decompressing text...') raw_txt = decompress(stream) diff --git a/src/calibre/gui2/convert/pdb_input.py b/src/calibre/gui2/convert/pdb_input.py deleted file mode 100644 index 16ff1ff236..0000000000 --- a/src/calibre/gui2/convert/pdb_input.py +++ /dev/null @@ -1,25 +0,0 @@ -# -*- coding: utf-8 -*- - -__license__ = 'GPL 3' -__copyright__ = '2011, John Schember ' -__docformat__ = 'restructuredtext en' - -from calibre.gui2.convert.txt_input_ui import Ui_Form -from calibre.gui2.convert import Widget - -class PluginWidget(Widget, Ui_Form): - - TITLE = _('PDB Input') - HELP = _('Options specific to')+' PDB '+_('input') - COMMIT_NAME = 'pdb_input' - ICON = I('mimetypes/txt.png') - - def __init__(self, parent, get_option, get_help, db=None, book_id=None): - Widget.__init__(self, parent, - ['paragraph_type', 'formatting_type', 'markdown_disable_toc', 'preserve_spaces']) - self.db, self.book_id = db, book_id - for x in get_option('paragraph_type').option.choices: - self.opt_paragraph_type.addItem(x) - for x in get_option('formatting_type').option.choices: - self.opt_formatting_type.addItem(x) - self.initialize_options(get_option, get_help, db, book_id) diff --git a/src/calibre/gui2/convert/tcr_input.py b/src/calibre/gui2/convert/tcr_input.py deleted file mode 100644 index 366643ad5b..0000000000 --- a/src/calibre/gui2/convert/tcr_input.py +++ /dev/null @@ -1,25 +0,0 @@ -# -*- coding: utf-8 -*- - -__license__ = 'GPL 3' -__copyright__ = '2011, John Schember ' -__docformat__ = 'restructuredtext en' - -from calibre.gui2.convert.txt_input_ui import Ui_Form -from calibre.gui2.convert import Widget - -class PluginWidget(Widget, Ui_Form): - - TITLE = _('TCR Input') - HELP = _('Options specific to')+' TCR '+_('input') - COMMIT_NAME = 'tcr_input' - ICON = I('mimetypes/txt.png') - - def __init__(self, parent, get_option, get_help, db=None, book_id=None): - Widget.__init__(self, parent, - ['paragraph_type', 'formatting_type', 'markdown_disable_toc', 'preserve_spaces']) - self.db, self.book_id = db, book_id - for x in get_option('paragraph_type').option.choices: - self.opt_paragraph_type.addItem(x) - for x in get_option('formatting_type').option.choices: - self.opt_formatting_type.addItem(x) - self.initialize_options(get_option, get_help, db, book_id) From 1786820728f1d69d2f5c5bf2ffd4d8f50f4b0219 Mon Sep 17 00:00:00 2001 From: John Schember Date: Thu, 6 Jan 2011 20:07:09 -0500 Subject: [PATCH 2/4] PDB PDF Input: Dynamically set options based on PDF plugin. --- src/calibre/ebooks/pdb/pdf/reader.py | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/src/calibre/ebooks/pdb/pdf/reader.py b/src/calibre/ebooks/pdb/pdf/reader.py index c151551866..30b0c4c57c 100644 --- a/src/calibre/ebooks/pdb/pdf/reader.py +++ b/src/calibre/ebooks/pdb/pdf/reader.py @@ -19,9 +19,6 @@ class Reader(FormatReader): self.stream = stream self.log = log self.options = options - setattr(self.options, 'new_pdf_engine', False) - setattr(self.options, 'no_images', False) - setattr(self.options, 'unwrap_factor', 0.45) def extract_content(self, output_dir): self.log.info('Extracting PDF...') @@ -31,7 +28,12 @@ class Reader(FormatReader): for x in xrange(self.header.section_count()): pdf.write(self.header.section_data(x)) - from calibre.customize.ui import plugin_for_input_format - pdf.seek(0) - return plugin_for_input_format('pdf').convert(pdf, self.options, - 'pdf', self.log, []) + from calibre.customize.ui import plugin_for_input_format + + pdf_plugin = plugin_for_input_format('pdf') + for option in pdf_plugin.options: + if not hasattr(self.options, option.option.name): + setattr(self.options, option.name, option.recommended_value) + + pdf.seek(0) + return pdf_plugin.convert(pdf, self.options, 'pdf', self.log, {}) From b5599f8ff2a9006d4312a9c88451afaf6001e41d Mon Sep 17 00:00:00 2001 From: John Schember Date: Thu, 6 Jan 2011 20:51:28 -0500 Subject: [PATCH 3/4] Fix indents. --- src/calibre/ebooks/conversion/preprocess.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/src/calibre/ebooks/conversion/preprocess.py b/src/calibre/ebooks/conversion/preprocess.py index 3ff816b3bf..9a27274dd8 100644 --- a/src/calibre/ebooks/conversion/preprocess.py +++ b/src/calibre/ebooks/conversion/preprocess.py @@ -51,16 +51,16 @@ def chap_head(match): chap = match.group('chap') title = match.group('title') if not title: - return '

'+chap+'


\n' + return '

'+chap+'


\n' else: - return '

'+chap+'

\n

'+title+'

\n' + return '

'+chap+'

\n

'+title+'

\n' def wrap_lines(match): ital = match.group('ital') if not ital: - return ' ' + return ' ' else: - return ital+' ' + return ital+' ' class DocAnalysis(object): ''' @@ -191,7 +191,7 @@ class Dehyphenator(object): dehyphenated = unicode(firsthalf) + unicode(secondhalf) lookupword = self.removesuffixes.sub('', dehyphenated) if self.prefixes.match(firsthalf) is None: - lookupword = self.removeprefix.sub('', lookupword) + lookupword = self.removeprefix.sub('', lookupword) #print "lookup word is: "+str(lookupword)+", orig is: " + str(hyphenated) try: searchresult = self.html.find(lookupword.lower()) From c7332d3651a54bf3d9a5890f08af0c6de6776acb Mon Sep 17 00:00:00 2001 From: John Schember Date: Thu, 6 Jan 2011 20:57:03 -0500 Subject: [PATCH 4/4] Fix indents. --- src/calibre/ebooks/conversion/utils.py | 40 +++++++++++++------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/src/calibre/ebooks/conversion/utils.py b/src/calibre/ebooks/conversion/utils.py index 11979b933c..a76ec8675d 100644 --- a/src/calibre/ebooks/conversion/utils.py +++ b/src/calibre/ebooks/conversion/utils.py @@ -113,24 +113,24 @@ class PreProcessor(object): # some lit files don't have any

tags or equivalent (generally just plain text between # 

 tags), check and  mark up line endings if required before proceeding
         if self.no_markup(html, 0.1):
-             self.log("not enough paragraph markers, adding now")
-             # check if content is in pre tags, use txt processor to mark up if so
-             pre = re.compile(r'
', re.IGNORECASE)
-             if len(pre.findall(html)) == 1:
-                 self.log("Running Text Processing")
-                 from calibre.ebooks.txt.processor import convert_basic, preserve_spaces, \
-                 separate_paragraphs_single_line
-                 outerhtml = re.compile(r'.*?(?<=
)(?P.*)(?=
).*', re.IGNORECASE|re.DOTALL)
-                 html = outerhtml.sub('\g', html)
-                 html = separate_paragraphs_single_line(html)
-                 html = preserve_spaces(html)
-                 html = convert_basic(html, epub_split_size_kb=0)
-             else:
-                 # Add markup naively
-                 # TODO - find out if there are cases where there are more than one 
 tag or
-                 # other types of unmarked html and handle them in some better fashion
-                 add_markup = re.compile('(?)(\n)')
-                 html = add_markup.sub('
\n
', html)
+            self.log("not enough paragraph markers, adding now")
+            # check if content is in pre tags, use txt processor to mark up if so
+            pre = re.compile(r'
', re.IGNORECASE)
+            if len(pre.findall(html)) == 1:
+                self.log("Running Text Processing")
+                from calibre.ebooks.txt.processor import convert_basic, preserve_spaces, \
+                separate_paragraphs_single_line
+                outerhtml = re.compile(r'.*?(?<=
)(?P.*)(?=
).*', re.IGNORECASE|re.DOTALL)
+                html = outerhtml.sub('\g', html)
+                html = separate_paragraphs_single_line(html)
+                html = preserve_spaces(html)
+                html = convert_basic(html, epub_split_size_kb=0)
+            else:
+                # Add markup naively
+                # TODO - find out if there are cases where there are more than one 
 tag or
+                # other types of unmarked html and handle them in some better fashion
+                add_markup = re.compile('(?)(\n)')
+                html = add_markup.sub('
\n
', html)
 
         ###### Mark Indents/Cleanup ######
         #
@@ -164,8 +164,8 @@ class PreProcessor(object):
                 self.log("deleting blank lines")
                 html = blankreg.sub('', html)
             elif float(len(blanklines)) / float(len(lines)) > 0.40:
-               blanks_between_paragraphs = True
-               #print "blanks between paragraphs is marked True"
+                blanks_between_paragraphs = True
+                #print "blanks between paragraphs is marked True"
             else:
                 blanks_between_paragraphs = False
         #self.dump(html, 'before_chapter_markup')