def lex(xmlstring):
"""
LEXs XML string.
Allows broken CDATA (pygments does not)
:param xmlstring:
:return: [XmlInterval]
"""
lexer = XmlLexer()
lokens = []
try:
tokens = lexer.get_tokens_unprocessed(xmlstring)
return list(_rejoin(tokens))
except _RejoinError as re:
# probably CDATA, will check in depth; hope no such pieces in attributes
lc = xmlstring.find("]]>")
lo = xmlstring.find("<![CDATA[")
rc = xmlstring.rfind("]]>")
ro = xmlstring.rfind("<![CDATA[")
if lc >= 0 and (lo == -1 or lo > lc):
# missing open CDATA
return lex("<![CDATA[" + xmlstring)[1:]
elif ro >= 0 and (rc == -1 or rc < ro):
# missing close CDATA
return lex(xmlstring + "]]>")[:-1]
except Exception as e:
logging.fatal("XML lexing:" + repr(e))
def highlightRML(rml):
lexer = XmlLexer()
styledRml = ''
for ttype, token in lexer.get_tokens(rml):
start, end = STYLES_FORMATTING.get(ttype, ('', ''))
styledRml += start + saxutils.escape(token) + end
return styledRml
def highlightRML(rml):
lexer = XmlLexer()
styledRml = ''
for ttype, token in lexer.get_tokens(rml):
start, end = STYLES_FORMATTING.get(ttype, ('', ''))
styledRml += start + saxutils.escape(token) + end
return styledRml
def lex(xmlstring):
"""
LEXs XML string.
Allows broken CDATA (pygments does not)
:param xmlstring:
:return: [XmlInterval]
"""
lexer = XmlLexer()
lokens = []
try:
tokens = lexer.get_tokens_unprocessed(xmlstring)
return list(_rejoin(tokens))
except _RejoinError as re:
# probably CDATA, will check in depth; hope no such pieces in attributes
lc = xmlstring.find("]]>")
lo = xmlstring.find("<![CDATA[")
rc = xmlstring.rfind("]]>")
ro = xmlstring.rfind("<![CDATA[")
if lc >= 0 and (lo == -1 or lo > lc):
# missing open CDATA
return lex("<![CDATA[" + xmlstring)[1:]
elif ro >= 0 and (rc == -1 or rc < ro):
# missing close CDATA
return lex(xmlstring + "]]>")[:-1]
except Exception as e:
logging.fatal("XML lexing:" + repr(e))
def highlight(src, syntax="python"):
# type: (t.Text, t.Text) -> t.Text
"""Apply syntax highlighting. Only available if pygments is installed."""
if syntax == "xml":
src = " " * 80 + src
src = textwrap.dedent(src).strip()
if not config.color:
return src
try:
from pygments import highlight as pyg_highlight
from pygments.lexers import PythonLexer, XmlLexer, RstLexer
from pygments.formatters.terminal import TerminalFormatter
except ImportError:
return src
else:
if syntax == "python":
lexer = PythonLexer()
elif syntax == "xml":
lexer = XmlLexer()
elif syntax == "rst":
lexer = RstLexer()
else:
raise ValueError("Unknown syntax {!r}".format(syntax))
return pyg_highlight(src, lexer,
TerminalFormatter()).strip() # type: ignore
def get_revision(request, entity_id, rev):
entity = get_object_or_404(Entity, id=entity_id)
md = entity.metadata.get_revision(rev)
formatter = HtmlFormatter(linenos=True)
html = HTML_WRAPPER % (entity_id, rev, highlight(md, XmlLexer(),
formatter))
return HttpResponse(html.encode(settings.DEFAULT_CHARSET))
def xml_highlight(xml_string):
if xml_string:
formated_xml = format_xml(xml_string)
highlight_xml = highlight(formated_xml, XmlLexer(), HtmlFormatter(linenos=True))
return highlight_xml
else:
return ''
def display_xml_nice(xml):
formatter = HtmlFormatter()
IPython.display.display(
HTML('<style type="text/css">{}</style> {}'.format(
formatter.get_style_defs(".highlight"),
highlight(xml, XmlLexer(), formatter),
)))
def pretty_format_data(data, content_type=False):
if data:
if content_type:
return highlight(data, XmlLexer(), HtmlFormatter())
else:
return highlight(json.dumps(data, indent=4), JsonLexer(),
HtmlFormatter())
def main():
"""
Main function to excecute everything in order
"""
parser = argparse.ArgumentParser(
description=
"Command-line tool to validate and pretty-print JSON and XML")
parser.add_argument("-x", action="store_true", help="Data is XML")
parser.add_argument("-b", action="store_true", help="Read data in chunks")
args = parser.parse_args()
if args.x and args.b:
sys.stderr.write("-x and -b cannot be used simultaneously\n")
exit(1)
elif args.b:
for line in sys.stdin:
print(color_yo_shit(format_code(line), JSONLexer()))
else:
data = sys.stdin.read()
if sys.stdout.isatty():
try:
data = color_yo_shit(format_code(data, args.x),
XmlLexer() if args.x else JSONLexer())
except ValueError as e:
print e
print(data)
def xml(xml_element: ET.Element) -> DisplayHandle:
formatter = HtmlFormatter()
xml_indented = ET.tostring(
xml_element, pretty_print=True, encoding='unicode')
style = formatter.get_style_defs('.highlight')
code = highlight(xml_indented, XmlLexer(), formatter)
return display(HTML(f'<style type="text/css">{style}</style> {code}'))
def renderXML(context, xml):
hformat = HtmlFormatter()
body = highlight(prettify_xml(xml), XmlLexer(), hformat)
env = Environment(loader=FileSystemLoader(context.confDirPath))
template_file = 'xml_render.html'
template = env.get_template(template_file)
return template.render(body=body)
def item_description(self, item):
if item.metadata:
formatter = HtmlFormatter(linenos=False,
outencoding=settings.DEFAULT_CHARSET)
if item.has_metadata():
xml = item.metadata.read()
return highlight(xml, XmlLexer(), formatter)
else:
return ugettext(u'No metadata yet')
def do_schema(self, line):
"""schema
prints the schema of the current index
"""
schema = self.solr.schema()
print highlight(schema,
formatter=TerminalFormatter(),
lexer=XmlLexer()).rstrip()
def do_fields(self, line):
"""fields
prints the fields of the current schema
"""
schema = self.solr.schema()
search = re.search(r'<fields>.*?</fields>', schema, re.DOTALL)
print highlight(search.group(0),
formatter=TerminalFormatter(),
lexer=XmlLexer()).rstrip()
def pprint_xml(xml_str, color=False):
proc = subprocess.Popen(shlex.split('xmllint --format -'),
stdin=subprocess.PIPE,
stdout=subprocess.PIPE)
(stdout, stderr) = proc.communicate(xml_str)
if color:
text = highlight(stdout, XmlLexer(), TerminalFormatter())
else:
text = stdout
print(text)
def highlight_xml(context, xml):
"""render XML as highlighted HTML"""
hformat = HtmlFormatter()
css = hformat.get_style_defs('.highlight')
body = highlight(prettify_xml(xml), XmlLexer(), hformat)
env = Environment(loader=FileSystemLoader(context.ppath))
template_file = 'resources/templates/xml_highlight.html'
template = env.get_template(template_file)
return template.render(css=css, body=body)
def pygmentize(text, format):
"""Returns respective HTML snippet of a source code aimed to be highlighted."""
if format == "n3" or format == "turtle" or format == "nt" or format == "nquads":
lexer = Notation3Lexer()
elif format == "rdfa" or format == "microdata":
lexer = HtmlLexer()
elif format == "pretty-xml" or format == "xml" or format == "trix":
lexer = XmlLexer()
elif format == "rdf-json" or format == "rdf-json-pretty" or format == "json-ld":
lexer = JsonLexer()
else:
lexer = guess_lexer(text)
return highlight(text, lexer, HtmlFormatter())
def item_description(self, item):
entity = item['entity']
current = item['revision']['versionid']
formatter = HtmlFormatter(linenos=True,
outencoding=settings.DEFAULT_CHARSET)
if 'previous' in item['revision']:
previous = item['revision']['previous']
diff = entity.metadata.get_diff(previous, current)
html = highlight(diff, DiffLexer(), formatter)
else:
xml = entity.metadata.get_revision(current)
html = highlight(xml, XmlLexer(), formatter)
return html
def print_proc_entitlements(self):
""" Get the plist embedded inside the process' __LINKEDIT section. """
linkedit_section = self.target.modules[0].FindSection('__LINKEDIT')
linkedit_data = self.symbol(
linkedit_section.GetLoadAddress(self.target)).peek(
linkedit_section.size)
# just look for the xml start inside the __LINKEDIT section. should be good enough since wer'e not
# expecting any other XML there
entitlements = str(
linkedit_data[linkedit_data.find(b'<?xml'):].split(b'\xfa', 1)[0],
'utf8')
print(highlight(entitlements, XmlLexer(),
TerminalTrueColorFormatter()))
def highlight_content(context, content, mimetype):
"""render content as highlighted HTML"""
hformat = HtmlFormatter()
css = hformat.get_style_defs('.highlight')
if mimetype == 'json':
body = highlight(json.dumps(content, indent=4), JsonLexer(), hformat)
elif mimetype == 'xml':
body = highlight(prettify_xml(content), XmlLexer(), hformat)
env = Environment(loader=FileSystemLoader(context.ppath))
template_file = 'resources/templates/api_highlight.html'
template = env.get_template(template_file)
return template.render(css=css, body=body)
def main():
"""
Main function to execute everything in order
"""
import argparse
from pygments.lexers import JsonLexer, XmlLexer
from pjson.core import format_code, color_yo_shit
parser = argparse.ArgumentParser(description="Command-line tool to "
"validate and pretty-print JSON and XML")
parser.add_argument("-x", action="store_true", help="Data is XML")
parser.add_argument("-b", action="store_true", help="Read data in chunks")
parser.add_argument("-t",
action="store_true",
help="Colorize regardless "
"if output is a terminal")
args = parser.parse_args()
if args.x and args.b:
sys.stderr.write("-x and -b cannot be used simultaneously\n")
parser.print_usage(sys.stderr)
exit(1)
colorize = args.t or sys.stdout.isatty()
if args.b:
for line in sys.stdin:
text = format_code(line)
if colorize:
text = color_yo_shit(text, JsonLexer())
print(text)
else:
data = sys.stdin.read()
try:
text = format_code(data, args.x)
if colorize:
text = color_yo_shit(
text,
XmlLexer() if args.x else JsonLexer()).rstrip('\r\n')
print(text)
except (ValueError, ET.ParseError) as e:
message = str(e)
if colorize:
red = '\x1b[31;m'
reset_colors = '\x1b[0;m'
message = ''.join([red, message, reset_colors])
sys.stderr.write(message + '\n')
exit(1)
def view_xml(self, m=None):
if not self.dock_window:
self.dock_window = TextEditor(self)
self.iface.mainWindow().addDockWidget(Qt.BottomDockWidgetArea,
self.dock_window)
if not self.using_mapnik:
# http://trac.osgeo.org/qgis/changeset/12955 - render starting signal
QObject.connect(self.canvas,
SIGNAL("renderComplete(QPainter *)"),
self.checkLayers)
self.dock_window.show()
if self.loaded_mapfile:
# if we have loaded a map xml or mml
# so lets just display the active file
xml = open(self.loaded_mapfile, 'rb').read()
else:
if not m:
# regenerate from qgis objects
e_c = sync.EasyCanvas(self, self.canvas)
m = e_c.to_mapnik()
if hasattr(mapnik, 'save_map_to_string'):
xml = mapnik.save_map_to_string(m)
else:
(handle, mapfile) = tempfile.mkstemp('.xml', 'quantumnik-map-')
os.close(handle)
mapnik.save_map(m, str(mapfile))
xml = open(mapfile, 'rb').read()
e = self.canvas.extent()
bbox = '%s %s %s %s' % (e.xMinimum(), e.yMinimum(), e.xMaximum(),
e.yMaximum())
cmd = '\n<!-- nik2img.py mapnik.xml out.png -d %s %s -e %s -->\n' % (
self.canvas.width(), self.canvas.height(), bbox)
try:
if self.mapnik_map:
cmd += '<!-- <MinScaleDenominator>%s</MinScaleDenominator> -->\n' % (
self.mapnik_map.scale_denominator())
except:
pass
code = xml + cmd
if HIGHLIGHTING:
highlighted = highlight(
code, XmlLexer(),
HtmlFormatter(linenos=False, nowrap=False, full=True))
self.dock_window.textEdit.setHtml(highlighted)
else:
self.dock_window.textEdit.setText(xml + cmd)
def view_source(self, req, resp, url):
"""
View the highlighted source (from `action_view`).
"""
content_type = resp.content_type
if content_type.startswith('application/xml'):
lexer = XmlLexer()
elif content_type == 'text/html':
lexer = HtmlLexer()
else:
## FIXME: what then?
lexer = HtmlLexer()
text = pygments_highlight(
resp.body, lexer,
HtmlFormatter(full=True, linenos=True, lineanchors='code'))
return Response(text)
def print_config(output, config_spec):
tree = output.simulation(0).config()
if config_spec:
expr = '//*[local-name() = $name]'
snippets = tree.xpath(expr, name=config_spec)
else:
snippets = [tree]
for i, what in enumerate(snippets):
if i > 0:
print()
text = etree.tostring(what, encoding='unicode')
if sys.stdout.isatty():
formatter = Terminal256Formatter()
print(highlight(text, XmlLexer(), formatter))
else:
print(text)
def xml(self, code):
code = code.strip('\n') + '\n'
self.snippet(code, line_numbers=False)
return self
with self._lock:
self.update_terminal_width()
if not self.terminal_colors:
self(code).nl()
else:
try:
from pygments import highlight
from pygments.lexers import XmlLexer
from pygments.formatters import TerminalFormatter
except ImportError:
self(xml).nl()
else:
hcode = highlight(code, XmlLexer(), TerminalFormatter())
self(hcode)
return self
def __update_window(self, width, height, message_no, page_no):
""" Update the window with the menu and the new text """
file_exists_label = '-F-ILE'
if not os.path.exists(self.__create_file_name(message_no)):
file_exists_label = '(f)ile'
# Clear the screen
if PLATFORM == 'win32':
# Ugly hack until someone figures out a better way for Windows
# probably something with a cls command, but I cannot test it
for _ in range(50):
print
else:
sys.stdout.write('\x1b[2J\x1b[H') # Clear screen
# Content
content = self.messages[message_no].output.rstrip('\n')
out = content
if self.args.color:
out = pygments.highlight(content, XmlLexer(), TerminalFormatter())
# Paging functionality
if message_no not in self.pages:
self._form_pages(message_no, content, out, height, width)
# Coerce in range
page_no = max(min(len(self.pages[message_no]) - 1, page_no), 0)
page_content = self.pages[message_no][page_no]
# Menu
max_message = str(len(self.messages) - 1)
position_string = u'{{0: >{0}}}/{{1: <{0}}}'.format(len(max_message))
position_string = position_string.format(message_no, max_message)
# Assume less than 100 pages
current_max_page = len(self.pages[message_no]) - 1
pages_string = u'{0: >2}/{1: <2}'.format(page_no, current_max_page)
menu = (u'(b)rowser | {0} | Message {1} \u2193 (s)\u2191 (w) | '
u'Page {2} \u2190 (a)\u2192 (d) | (q)uit\n{3}').\
format(file_exists_label, position_string, pages_string,
'-' * width)
print menu
print page_content
return page_no
def info(heritrix_conf, jobname, raw):
"""Show information about all jobs or a single job.
If given a jobname as argument then only display information about this job.
Tries to use ``pygments`` to colorize the output."""
import json
api = heritrix_conf.api
try:
if raw:
info = api.info(job_name=jobname, raw=True).text
else:
info = api.info(job_name=jobname, raw=False)
info = json.dumps(info, indent=2)
except HeritrixAPIError as ex:
click.echo(f"Error: {ex}", err=True)
raise click.Abort()
if raw:
try:
from pygments import highlight
from pygments.formatters import TerminalFormatter
from pygments.lexers import XmlLexer
info = highlight(info, XmlLexer(), TerminalFormatter())
except ImportError:
pass
else:
try:
from pygments import highlight
from pygments.formatters import TerminalFormatter
from pygments.lexers import JsonLexer
info = highlight(info, JsonLexer(), TerminalFormatter())
except ImportError:
pass
click.echo(info)
import sys, time, os, lxml.etree as etree, re
from parse_bill import parse
from watchdog.observers import Observer
from watchdog.events import FileSystemEventHandler, FileCreatedEvent, DirCreatedEvent
from pygments.lexers import XmlLexer
from pygments.formatters import HtmlFormatter
from pygments import highlight
from shutil import rmtree
def is_docx(path):
base = os.path.basename(path)
return path.endswith('.docx') and not base.startswith('~')
xml_lexer = XmlLexer()
html_formatter = HtmlFormatter(style='igor')
error_re = re.compile(r'errors="(\d+)"')
class EventHandler(FileSystemEventHandler):
def __init__(self, in_path, out_path):
self.in_path = in_path
self.out_path = out_path
def make_index(self, src_path):
pyg_path = self.pygments_path(src_path)
children = os.listdir(pyg_path)
html = '<ul>'
for child in children:
def print_xml(xml_str: str):
formatter = HtmlFormatter()
IPython.display.display(
HTML('<style type="text/css">{}</style> {}'.format(
formatter.get_style_defs('.highlight'),
highlight(xml_str, XmlLexer(), formatter))))
idx += 1
else: # inside comment
if i.int_type == IntervalType.general and not i.name and i.srepr == '-->':
current_comment += i.srepr
inside_comment = False
yield XmlInterval(IntervalType.comment, current_comment_offs,
current_comment, None, idx)
idx += 1
current_comment_offs = 0
else:
current_comment += i.srepr
# just for testing purposes, TODO: remove it completely
if __name__ == '__main__':
lexer = XmlLexer()
s = ''
# with open("tmpFile4CloneFinding.txt", encoding='utf-8') as f: s = f.read()
# s = '<tag><![CDATA[cdata with <tag></tag> here]]></tag>'
# s = '<![CDATA[<t cdata with <tag></tag> here]]></tag>'
# s = '''very broken]> ]]><