def convert_to_pango(txt, headers=None, options=None):
'''
Code partly taken from txt2tags tarball
'''
original_txt = txt
# Here is the marked body text, it must be a list.
txt = txt.split('\n')
# Set the three header fields
if headers is None:
headers = ['', '', '']
config = txt2tags.ConfigMaster()._get_defaults()
config['outfile'] = txt2tags.MODULEOUT # results as list
config['target'] = 'xhtml'
config['preproc'] = []
# We need to escape the ampersand here, otherwise "&" would become
# "&"
config['preproc'].append([r'&', '&'])
# Allow line breaks
config['postproc'] = []
config['postproc'].append([REGEX_LINEBREAK, '\n'])
if options is not None:
config.update(options)
# Let's do the conversion
try:
body, toc = txt2tags.convert(txt, config)
full_doc = body
finished = txt2tags.finish_him(full_doc, config)
result = ''.join(finished)
# Txt2tags error, show the messsage to the user
except txt2tags.error, msg:
logging.error(msg)
result = msg
def convert_to_pango(txt, headers=None, options=None):
"""
Code partly taken from txt2tags tarball
"""
original_txt = txt
# Here is the marked body text, it must be a list.
txt = txt.split("\n")
# Set the three header fields
if headers is None:
headers = ["", "", ""]
config = txt2tags.ConfigMaster()._get_defaults()
config["outfile"] = txt2tags.MODULEOUT # results as list
config["target"] = "xhtml"
config["preproc"] = []
# We need to escape the ampersand here, otherwise "&" would become
# "&"
config["preproc"].append([r"&", "&"])
# Allow line breaks
config["postproc"] = []
config["postproc"].append([REGEX_LINEBREAK, "\n"])
if options is not None:
config.update(options)
# Let's do the conversion
try:
body, toc = txt2tags.convert(txt, config)
full_doc = body
finished = txt2tags.finish_him(full_doc, config)
result = "".join(finished)
# Txt2tags error, show the messsage to the user
except txt2tags.error as msg:
logging.error(msg)
result = msg
# Unknown error, show the traceback to the user
except Exception:
result = txt2tags.getUnknownErrorMessage()
logging.error(result)
# remove unwanted paragraphs
result = result.replace("<p>", "").replace("</p>", "")
logging.log(
5,
'Converted "%s" text to "%s" txt2tags markup'
% (repr(original_txt), repr(result)),
)
# Remove unknown tags (<a>)
def replace_links(match):
"""Return the link name."""
return match.group(1)
result = re.sub(REGEX_HTML_LINK, replace_links, result)
try:
Pango.parse_markup(result, -1, "0")
# result is valid pango markup, return the markup.
return result
except GObject.GError:
# There are unknown tags in the markup, return the original text
logging.debug("There are unknown tags in the markup: %s" % result)
return original_txt
def _get_config(target, options):
# Set the configuration on the 'config' dict.
config = txt2tags.ConfigMaster()._get_defaults()
config["outfile"] = txt2tags.MODULEOUT # results as list
config["target"] = target
# The Pre (and Post) processing config is a list of lists:
# [ [this, that], [foo, bar], [patt, replace] ]
config["postproc"] = []
config["preproc"] = []
config["style"] = []
# Allow line breaks, r'\\\\' are 2 \ for regexes
config["preproc"].append([REGEX_LINEBREAK, "LINEBREAK"])
# Highlight hashtags.
if target == "tex":
config["preproc"].append(
[HASHTAG.pattern, r"\1{\2\3BEGININDEX\3ENDINDEX|color:red}"]
)
else:
config["preproc"].append([HASHTAG.pattern, r"\1{\2\3|color:red}"])
# Escape color markup.
config["preproc"].append([r"\{(.*?)\|color:(.+?)\}", ESCAPE_COLOR])
if target in ["xhtml", "html"]:
config["encoding"] = "UTF-8" # document encoding
config["toc"] = 0
config["css-sugar"] = 1
# Fix encoding for export opened in firefox
config["postproc"].append([r"<head>", "<head>" + CHARSET_UTF8])
# Line breaks
config["postproc"].append([r"LINEBREAK", "<br />"])
# Apply image resizing
config["postproc"].append([r"src=\"WIDTH(\d+)-", r'width="\1" src="'])
# {{red text|color:red}} -> <span style="color:red">red text</span>
config["postproc"].append([COLOR_ESCAPED, r'<span style="color:\2">\1</span>'])
# Custom css
font = options.pop("font", "sans-serif")
css = CSS % {
"font": font,
"bgcolor": options.get("bgcolor", "white"),
"fgcolor": options.get("fgcolor", "black"),
}
config["postproc"].append([r"</head>", css + "</head>"])
# MathJax
if options.pop("add_mathjax"):
config["postproc"].append([r"</body>", MATHJAX + "</body>"])
elif target == "tex":
config["encoding"] = "utf8"
config["preproc"].append(["€", "Euro"])
# Latex only allows whitespace and underscores in filenames if
# the filename is surrounded by "...". This is in turn only possible
# if the extension is omitted.
config["preproc"].append([r'\[""', r'["""'])
config["preproc"].append([r'""\.', r'""".'])
scheme = filesystem.LOCAL_FILE_PEFIX
# For images we have to omit the file:// prefix
config["postproc"].append(
[r'includegraphics\{(.*)"%s' % scheme, r'includegraphics{"\1']
)
# Special handling for LOCAL file links (Omit scheme, add run:)
# \htmladdnormallink{file.txt}{file:///home/user/file.txt}
# -->
# \htmladdnormallink{file.txt}{run:/home/user/file.txt}
config["postproc"].append(
[
r"htmladdnormallink\{(.*)\}\{%s(.*)\}" % scheme,
r"htmladdnormallink{\1}{run:\2}",
]
)
# Line breaks
config["postproc"].append([r"LINEBREAK", r"\\\\"])
# Apply image resizing
config["postproc"].append(
[r'includegraphics\{("?)WIDTH(\d+)-', r"includegraphics[width=\2px]{\1"]
)
# We want the plain latex formulas unescaped.
# Allowed formulas: $$...$$, \[...\], \(...\)
config["preproc"].append(
[r"\\\[\s*(.+?)\s*\\\]", r"BEGINEQUATION''\1''ENDEQUATION"]
)
config["preproc"].append(
[r"\$\$\s*(.+?)\s*\$\$", r"BEGINEQUATION''\1''ENDEQUATION"]
)
config["postproc"].append([r"BEGINEQUATION(.+)ENDEQUATION", r"$$\1$$"])
config["preproc"].append([r"\\\(\s*(.+?)\s*\\\)", r"BEGINMATH''\1''ENDMATH"])
config["postproc"].append([r"BEGINMATH(.+)ENDMATH", r"$\1$"])
# Fix utf8 quotations - „, “ and ” cause problems compiling the latex document.
config["postproc"].extend([["„", '"'], ["”", '"'], ["“", '"']])
# Enable index.
config["style"].append("makeidx")
config["postproc"].append([r"BEGININDEX(.+?)ENDINDEX", r"\\index{\1}"])
config["postproc"].append(["begin{document}", "makeindex\n\\\\begin{document}"])
config["postproc"].append(["end{document}", "printindex\n\n\\\\end{document}"])
config["postproc"].append([COLOR_ESCAPED, r"\\textcolor{\2}{\1}"])
elif target == "txt":
# Line breaks
config["postproc"].append([r"LINEBREAK", "\n"])
# Apply image resizing ([WIDTH400-file:///pathtoimage.jpg])
config["postproc"].append([r"\[WIDTH(\d+)-(.+)\]", r"[\2?\1]"])
# Entry references
if target in ["xhtml", "html"]:
# txt2tags will generate links to the named entry references because they share common bracket
# notation used by the URIs. We just need to add our internal schema to make it a proper URI.
config["preproc"].append(
[
r"\[(?P<name>.+)\s+(?P<date>\d{4}-\d{2}-\d{2})\s*\]",
r"[\g<name> #\g<date>]",
]
)
# Convert bracketed dates into named references where the date itself is being used as a name.
# For example:
# "Today is [2019-10-20]" will be converted into "Today is [2019-10-20 #2019-10-20]"
config["preproc"].append(
[r"\[(?P<date>\d{4}-\d{2}-\d{2})\]", r"[\g<date> #\g<date>]"]
)
else:
# Links to entry references are not supported for targets other than (X)HTML
config["preproc"].append(
[r"\[(?P<name>.+)\s+(?P<date>\d{4}-\d{2}-\d{2})\]", r"\g<name> (\g<date>)"]
)
# Allow resizing images by changing
# [filename.png?width] to [WIDTHwidth-filename.png]
img_ext = r"png|jpe?g|gif|eps|bmp|svg"
img_name = r"\S.*\S|\S"
# Apply this prepoc only after the latex image quotes have been added
config["preproc"].append(
[r"\[({}\.({}))\?(\d+)\]".format(img_name, img_ext), r"[WIDTH\3-\1]"]
)
# Disable colors for all other targets.
config["postproc"].append([COLOR_ESCAPED, r"\1"])
config.update(options)
return config
def _get_config(target, options):
config = {}
# Set the configuration on the 'config' dict.
config = txt2tags.ConfigMaster()._get_defaults()
config['outfile'] = txt2tags.MODULEOUT # results as list
config['target'] = target
# The Pre (and Post) processing config is a list of lists:
# [ [this, that], [foo, bar], [patt, replace] ]
config['postproc'] = []
config['preproc'] = []
config['style'] = []
# Allow line breaks, r'\\\\' are 2 \ for regexes
config['preproc'].append([REGEX_LINEBREAK, 'LINEBREAK'])
# Highlight hashtags.
if target == 'tex':
config['preproc'].append(
[HASHTAG.pattern, r'\1{\2\3BEGININDEX\3ENDINDEX|color:red}'])
else:
config['preproc'].append([HASHTAG.pattern, r'\1{\2\3|color:red}'])
# Escape color markup.
config['preproc'].append([r'\{(.*?)\|color:(.+?)\}', ESCAPE_COLOR])
if target in ['xhtml', 'html']:
config['encoding'] = 'UTF-8' # document encoding
config['toc'] = 0
config['css-sugar'] = 1
# Fix encoding for export opened in firefox
config['postproc'].append([r'<head>', '<head>' + CHARSET_UTF8])
# Line breaks
config['postproc'].append([r'LINEBREAK', '<br />'])
# Apply image resizing
config['postproc'].append([r'src=\"WIDTH(\d+)-', r'width="\1" src="'])
# {{red text|color:red}} -> <span style="color:red">red text</span>
config['postproc'].append(
[COLOR_ESCAPED, r'<span style="color:\2">\1</span>'])
elif target == 'tex':
config['encoding'] = 'utf8'
config['preproc'].append(['€', 'Euro'])
# Latex only allows whitespace and underscores in filenames if
# the filename is surrounded by "...". This is in turn only possible
# if the extension is omitted.
config['preproc'].append([r'\[""', r'["""'])
config['preproc'].append([r'""\.', r'""".'])
scheme = 'file:///' if sys.platform == 'win32' else 'file://'
# For images we have to omit the file:// prefix
config['postproc'].append(
[r'includegraphics\{(.*)"%s' % scheme, r'includegraphics{"\1'])
# Special handling for LOCAL file links (Omit scheme, add run:)
# \htmladdnormallink{file.txt}{file:///home/user/file.txt}
# -->
# \htmladdnormallink{file.txt}{run:/home/user/file.txt}
config['postproc'].append([
r'htmladdnormallink\{(.*)\}\{%s(.*)\}' % scheme,
r'htmladdnormallink{\1}{run:\2}'
])
# Line breaks
config['postproc'].append([r'LINEBREAK', r'\\\\'])
# Apply image resizing
config['postproc'].append([
r'includegraphics\{("?)WIDTH(\d+)-',
r'includegraphics[width=\2px]{\1'
])
# We want the plain latex formulas unescaped.
# Allowed formulas: $$...$$, \[...\], \(...\)
config['preproc'].append(
[r'\\\[\s*(.+?)\s*\\\]', r"BEGINEQUATION''\1''ENDEQUATION"])
config['preproc'].append(
[r'\$\$\s*(.+?)\s*\$\$', r"BEGINEQUATION''\1''ENDEQUATION"])
config['postproc'].append([r'BEGINEQUATION(.+)ENDEQUATION', r'$$\1$$'])
config['preproc'].append(
[r'\\\(\s*(.+?)\s*\\\)', r"BEGINMATH''\1''ENDMATH"])
config['postproc'].append([r'BEGINMATH(.+)ENDMATH', r'$\1$'])
# Fix utf8 quotations - „, “ and ” cause problems compiling the latex document.
config['postproc'].extend([[u'„', '"'], [u'”', '"'], [u'“', '"']])
# Enable index.
config['style'].append('makeidx')
config['postproc'].append([r'BEGININDEX(.+?)ENDINDEX', r'\\index{\1}'])
config['postproc'].append(
['begin{document}', 'makeindex\n\\\\begin{document}'])
config['postproc'].append(
['end{document}', 'printindex\n\n\\\\end{document}'])
config['postproc'].append([COLOR_ESCAPED, r'\\textcolor{\2}{\1}'])
elif target == 'txt':
# Line breaks
config['postproc'].append([r'LINEBREAK', '\n'])
# Apply image resizing ([WIDTH400-file:///pathtoimage.jpg])
config['postproc'].append([r'\[WIDTH(\d+)-(.+)\]', r'[\2?\1]'])
# Allow resizing images by changing
# [filename.png?width] to [WIDTHwidth-filename.png]
img_ext = r'png|jpe?g|gif|eps|bmp|svg'
img_name = r'\S.*\S|\S'
# Apply this prepoc only after the latex image quotes have been added
config['preproc'].append(
[r'\[(%s\.(%s))\?(\d+)\]' % (img_name, img_ext), r'[WIDTH\3-\1]'])
# Disable colors for all other targets.
config['postproc'].append([COLOR_ESCAPED, r'\1'])
# MathJax
if options.pop('add_mathjax'):
config['postproc'].append([r'</body>', MATHJAX + '</body>'])
config['postproc'].append([r'</body>', PRINT_FUNCTION + '</body>'])
# Custom css
fonts = options.pop('font', 'sans-serif')
if 'html' in target:
css = CSS % {'font': fonts, 'table_head_bg': TABLE_HEAD_BG}
config['postproc'].append([r'</head>', css + '</head>'])
config.update(options)
return config
def _get_config(type):
config = {}
# Set the configuration on the 'config' dict.
config = txt2tags.ConfigMaster()._get_defaults()
# The Pre (and Post) processing config is a list of lists:
# [ [this, that], [foo, bar], [patt, replace] ]
config['postproc'] = []
config['preproc'] = []
if type == 'xhtml' or type == 'html':
config['encoding'] = 'UTF-8' # document encoding
config['toc'] = 0
config['style'] = [
os.path.join(filesystem.files_dir, 'stylesheet.css')
]
config['css-inside'] = 1
config['css-sugar'] = 1
# keepnote only recognizes "<strike>"
config['postproc'].append(['(?i)(</?)s>', r'\1strike>'])
# Allow line breaks, r'\\\\' are 2 \ for regexes
config['postproc'].append([r'\\\\', '<br />'])
# Apply image resizing
config['postproc'].append([r'src=\"WIDTH(\d+)-', r'width="\1" src="'])
elif type == 'tex':
config['encoding'] = 'utf8'
config['preproc'].append(['€', 'Euro'])
# Latex only allows whitespace and underscores in filenames if
# the filename is surrounded by "...". This is in turn only possible
# if the extension is omitted
config['preproc'].append([r'\[""', r'["""'])
config['preproc'].append([r'""\.', r'""".'])
scheme = 'file:///' if sys.platform == 'win32' else 'file://'
# For images we have to omit the file:// prefix
config['postproc'].append(
[r'includegraphics\{(.*)"%s' % scheme, r'includegraphics{"\1'])
#config['postproc'].append([r'includegraphics\{"file://', r'includegraphics{"'])
# Special handling for LOCAL file links (Omit scheme, add run:)
# \htmladdnormallink{file.txt}{file:///home/user/file.txt}
# -->
# \htmladdnormallink{file.txt}{run:/home/user/file.txt}
config['postproc'].append([
r'htmladdnormallink\{(.*)\}\{%s(.*)\}' % scheme,
r'htmladdnormallink{\1}{run:\2}'
])
# Allow line breaks, r'\\\\' are 2 \ for regexes
config['postproc'].append([r'\$\\backslash\$\$\\backslash\$', r'\\\\'])
# Apply image resizing
config['postproc'].append([
r'includegraphics\{("?)WIDTH(\d+)-',
r'includegraphics[width=\2px]{\1'
])
elif type == 'txt':
# Allow line breaks, r'\\\\' are 2 \ for regexes
config['postproc'].append([r'\\\\', '\n'])
# Apply image resizing ([WIDTH400-file:///pathtoimage.jpg])
config['postproc'].append([r'\[WIDTH(\d+)-(.+)\]', r'[\2?\1]'])
# Allow resizing images by changing
# [filename.png?width] to [WIDTHwidth-filename.png]
img_ext = r'png|jpe?g|gif|eps|bmp'
img_name = r'\S.*\S|\S'
# Apply this prepoc only after the latex image quotes have been added
config['preproc'].append(
[r'\[(%s\.(%s))\?(\d+)\]' % (img_name, img_ext), r'[WIDTH\3-\1]'])
return config
