def extractone(self, params):
#self.em.rclog("extractone %s" % params["filename:"])
ok = False
if "filename:" not in params:
self.em.rclog("extractone: no file name")
return (ok, docdata, "", rclexecm.RclExecM.eofnow)
filename = params["filename:"]
try:
metadata = pyexiv2.ImageMetadata(filename)
metadata.read()
keys = metadata.exif_keys + metadata.iptc_keys + metadata.xmp_keys
mdic = {}
for k in keys:
# we skip numeric keys and undecoded makernote data
if k != 'Exif.Photo.MakerNote' and not khexre.match(k):
mdic[k] = str(metadata[k].raw_value)
except Exception as err:
self.em.rclog("extractone: extract failed: [%s]" % err)
return (ok, "", "", rclexecm.RclExecM.eofnow)
docdata = b'<html><head>\n'
ttdata = set()
for k in pyexiv2_titles:
if k in mdic:
ttdata.add(self.em.htmlescape(mdic[k]))
if ttdata:
title = ""
for v in ttdata:
v = v.replace('[', '').replace(']', '').replace("'", "")
title += v + " "
docdata += rclexecm.makebytes("<title>" + title + "</title>\n")
for k in exiv2_dates:
if k in mdic:
# Recoll wants: %Y-%m-%d %H:%M:%S.
# We get 2014:06:27 14:58:47
dt = mdic[k].replace(":", "-", 2)
docdata += b'<meta name="date" content="' + \
rclexecm.makebytes(dt) + b'">\n'
break
for k, v in mdic.items():
if k == 'Xmp.digiKam.TagsList':
docdata += b'<meta name="keywords" content="' + \
rclexecm.makebytes(self.em.htmlescape(mdic[k])) + \
b'">\n'
docdata += b'</head><body>\n'
for k, v in mdic.items():
docdata += rclexecm.makebytes(k + " : " + \
self.em.htmlescape(mdic[k]) + "<br />\n")
docdata += b'</body></html>'
self.em.setmimetype("text/html")
return (True, docdata, "", rclexecm.RclExecM.eofnext)
def extractone(self, params):
#self.em.rclog("extractone %s" % params["filename:"])
ok = False
if "filename:" not in params:
self.em.rclog("extractone: no file name")
return (ok, docdata, "", rclexecm.RclExecM.eofnow)
filename = params["filename:"]
try:
metadata = pyexiv2.ImageMetadata(filename)
metadata.read()
keys = metadata.exif_keys + metadata.iptc_keys + metadata.xmp_keys
mdic = {}
for k in keys:
# we skip numeric keys and undecoded makernote data
if k != 'Exif.Photo.MakerNote' and not khexre.match(k):
mdic[k] = str(metadata[k].raw_value)
except Exception as err:
self.em.rclog("extractone: extract failed: [%s]" % err)
return (ok, "", "", rclexecm.RclExecM.eofnow)
docdata = b'<html><head>\n'
ttdata = set()
for k in pyexiv2_titles:
if k in mdic:
ttdata.add(self.em.htmlescape(mdic[k]))
if ttdata:
title = ""
for v in ttdata:
v = v.replace('[', '').replace(']', '').replace("'", "")
title += v + " "
docdata += rclexecm.makebytes("<title>" + title + "</title>\n")
for k in exiv2_dates:
if k in mdic:
# Recoll wants: %Y-%m-%d %H:%M:%S.
# We get 2014:06:27 14:58:47
dt = mdic[k].replace(":", "-", 2)
docdata += b'<meta name="date" content="' + \
rclexecm.makebytes(dt) + b'">\n'
break
for k,v in mdic.items():
if k == 'Xmp.digiKam.TagsList':
docdata += b'<meta name="keywords" content="' + \
rclexecm.makebytes(self.em.htmlescape(mdic[k])) + \
b'">\n'
docdata += b'</head><body>\n'
for k,v in mdic.items():
docdata += rclexecm.makebytes(k + " : " + \
self.em.htmlescape(mdic[k]) + "<br />\n")
docdata += b'</body></html>'
self.em.setmimetype("text/html")
return (True, docdata, "", rclexecm.RclExecM.eofnext)
def format(self):
""" Parse and send the colored source.
"""
# store line offsets in self.lines
self.lines = [0, 0]
pos = 0
while 1:
pos = self.raw.find(b'\n', pos) + 1
if not pos: break
self.lines.append(pos)
self.lines.append(len(self.raw))
# parse the source and write it
self.pos = 0
text = io.BytesIO(self.raw)
self.out.write(rclexecm.makebytes(self.stylesheet))
self.out.write(b'<pre class="code">\n')
try:
for a,b,c,d,e in tokenize.tokenize(text.readline):
self(a,b,c,d,e)
except Exception as ex:
# There are other possible exceptions, for example for a
# bad encoding line (->SyntaxError). e.g. # -*- coding: lala -*-
self.out.write(("<h3>ERROR: %s</h3>\n" % ex).encode('utf-8'))
self.out.write(b'\n</pre>')
def html_text(self, filename):
ok = False
metadata = pyexiv2.ImageMetadata(filename)
metadata.read()
keys = metadata.exif_keys + metadata.iptc_keys + metadata.xmp_keys
mdic = {}
for k in keys:
# we skip numeric keys and undecoded makernote data
if k != 'Exif.Photo.MakerNote' and not khexre.match(k):
mdic[k] = str(metadata[k].raw_value)
docdata = b'<html><head>\n'
ttdata = set()
for k in pyexiv2_titles:
if k in mdic:
ttdata.add(rclexecm.htmlescape(mdic[k]))
if ttdata:
title = ""
for v in ttdata:
v = v.replace('[', '').replace(']', '').replace("'", "")
title += v + " "
docdata += rclexecm.makebytes("<title>" + title + "</title>\n")
for k in exiv2_dates:
if k in mdic:
# Recoll wants: %Y-%m-%d %H:%M:%S.
# We get 2014:06:27 14:58:47
dt = mdic[k].replace(":", "-", 2)
docdata += b'<meta name="date" content="' + \
rclexecm.makebytes(dt) + b'">\n'
break
for k,v in mdic.items():
if k == 'Xmp.digiKam.TagsList':
docdata += b'<meta name="keywords" content="' + \
rclexecm.makebytes(rclexecm.htmlescape(mdic[k])) + \
b'">\n'
docdata += b'</head><body>\n'
for k,v in mdic.items():
docdata += rclexecm.makebytes(k + " : " + \
rclexecm.htmlescape(mdic[k]) + "<br />\n")
docdata += b'</body></html>'
return docdata
def __call__(self, toktype, toktext, startpos, endpos, line):
""" Token handler.
"""
if 0:
print("type %s %s text %s start %s %s end %s %s<br>\n" % \
(toktype, token.tok_name[toktype], toktext, \
srow, scol,erow,ecol))
srow, scol = startpos
erow, ecol = endpos
# calculate new positions
oldpos = self.pos
newpos = self.lines[srow] + scol
self.pos = newpos + len(toktext)
# handle newlines
if toktype in [token.NEWLINE, tokenize.NL]:
self.out.write(b'\n')
return
# send the original whitespace, if needed
if newpos > oldpos:
self.out.write(self.raw[oldpos:newpos])
# skip indenting tokens
if toktype in [token.INDENT, token.DEDENT]:
self.pos = newpos
return
# map token type to a color group
if token.LPAR <= toktype and toktype <= token.OP:
toktype = token.OP
elif toktype == token.NAME and keyword.iskeyword(toktext):
toktype = _KEYWORD
css_class = _css_classes.get(toktype, 'text')
# send text
self.out.write(rclexecm.makebytes('<span class="%s">' % (css_class,)))
self.out.write(rclexecm.makebytes(html.escape(toktext)))
self.out.write(b'</span>')
def colorize_file(file=None, outstream=sys.stdout, standalone=True):
"""Convert a python source file into colorized HTML.
Reads file and writes to outstream (default sys.stdout). file can be a
filename or a file-like object (only the read method is used). If file is
None, act as a filter and read from sys.stdin. If standalone is True
(default), send a complete HTML document with header and footer. Otherwise
only a stylesheet and a <pre> section are written.
"""
from os.path import basename
if hasattr(file, 'read'):
sourcefile = file
file = None
try:
filename = basename(file.name)
except:
filename = 'STREAM'
elif file is not None:
try:
sourcefile = open(file, 'rb')
filename = basename(file)
except IOError:
raise SystemExit("File %s unknown." % file)
else:
sourcefile = sys.stdin
filename = 'STDIN'
source = sourcefile.read()
if standalone:
outstream.write(rclexecm.makebytes(_HTML_HEADER % {'title': filename}))
Parser(source, out=outstream).format()
if standalone:
outstream.write(rclexecm.makebytes(_HTML_FOOTER))
if file:
sourcefile.close()
def _metatag(self, nm, val):
return b"<meta name=\"" + rclexecm.makebytes(nm) + b"\" content=\"" + \
rclexecm.htmlescape(rclexecm.makebytes(val)) + b"\">"