[GRASS-SVN] r70285 - grass/trunk/tools/g.html2man
svn_grass at osgeo.org
svn_grass at osgeo.org
Fri Jan 6 11:40:09 PST 2017
Author: wenzeslaus
Date: 2017-01-06 11:40:09 -0800 (Fri, 06 Jan 2017)
New Revision: 70285
Added:
grass/trunk/tools/g.html2man/ggroff.py
grass/trunk/tools/g.html2man/ghtml.py
Removed:
grass/trunk/tools/g.html2man/groff.py
grass/trunk/tools/g.html2man/html.py
Modified:
grass/trunk/tools/g.html2man/Makefile
grass/trunk/tools/g.html2man/g.html2man.py
Log:
g.html2man: use unique mod names, open, items, and try imports for Python 3 compatibility
Modified: grass/trunk/tools/g.html2man/Makefile
===================================================================
--- grass/trunk/tools/g.html2man/Makefile 2017-01-06 18:59:14 UTC (rev 70284)
+++ grass/trunk/tools/g.html2man/Makefile 2017-01-06 19:40:09 UTC (rev 70285)
@@ -2,7 +2,7 @@
include $(MODULE_TOPDIR)/include/Make/Other.make
-TARGETS := $(patsubst %.py,$(TOOLSDIR)/%.py,html.py groff.py g.html2man.py)
+TARGETS := $(patsubst %.py,$(TOOLSDIR)/%.py,ghtml.py ggroff.py g.html2man.py)
default: $(TARGETS)
Modified: grass/trunk/tools/g.html2man/g.html2man.py
===================================================================
--- grass/trunk/tools/g.html2man/g.html2man.py 2017-01-06 18:59:14 UTC (rev 70284)
+++ grass/trunk/tools/g.html2man/g.html2man.py 2017-01-06 19:40:09 UTC (rev 70285)
@@ -1,10 +1,16 @@
#!/usr/bin/env python
import sys
import re
-from html import HTMLParser, HTMLParseError
-from groff import Formatter
-from StringIO import StringIO
+from ghtml import HTMLParser, HTMLParseError
+from ggroff import Formatter
+try:
+ # Python 2 str - bytes version
+ from StringIO import StringIO
+except ImportError:
+ # Python 3 str - unicode version
+ from io import StringIO
+
entities = {
'nbsp': " ",
'bull': "*"
@@ -32,7 +38,7 @@
def main():
# parse HTML
infile = sys.argv[1]
- inf = file(infile)
+ inf = open(infile)
p = HTMLParser(entities)
for n, line in enumerate(inf):
try:
@@ -63,7 +69,7 @@
s = s.lstrip()
# write groff
- outf = file(sys.argv[2], 'w')
+ outf = open(sys.argv[2], 'w')
outf.write(s)
outf.close()
Copied: grass/trunk/tools/g.html2man/ggroff.py (from rev 70284, grass/trunk/tools/g.html2man/groff.py)
===================================================================
--- grass/trunk/tools/g.html2man/ggroff.py (rev 0)
+++ grass/trunk/tools/g.html2man/ggroff.py 2017-01-06 19:40:09 UTC (rev 70285)
@@ -0,0 +1,271 @@
+
+import sys
+import os
+import re
+
+__all__ = ["Formatter"]
+
+try:
+ version = os.environ['VERSION_NUMBER']
+except:
+ version = ""
+
+styles = {
+ 'b': "\\fB@\\fR",
+ 'i': "\\fI@\\fR",
+ 'em': "\\fI@\\fR",
+ 'code': "\\fC@\\fR",
+ 'span': "\\fC@\\fR",
+ 'sup': "\\u@\\d",
+ 'hr': ""
+}
+
+formats = {
+ 'br': "\n.br\n",
+ 'h2': "\n.SH @",
+ 'h3': "\n.SS @",
+ 'h4': "\n.SS @",
+ 'dt': ("\n.IP \"@\" 4m", 'no_nl'),
+ 'dd': "\n.br\n@",
+ 'ul': ("\n.RS 4n\n@\n.RE\n", 'in_ul'),
+ 'menu': ("\n.RS 4n\n@\n.RE\n", 'in_ul'),
+ 'dir': ("\n.RS 4n\n@\n.RE\n", 'in_ul'),
+ 'ol': ("\n.IP\n@\n.PP\n", 'index'),
+ 'p': "\n.PP\n@",
+ 'pre': ("\n.br\n.nf\n\\fC\n@\n\\fR\n.fi\n", 'preformat')
+}
+
+formats.update(styles)
+
+
+def is_string(x):
+ return isinstance(x, str)
+
+
+def is_tuple(x):
+ return isinstance(x, tuple)
+
+
+def is_list(x):
+ return isinstance(x, list)
+
+
+def is_blank(s):
+ return is_string(s) and s.strip() == ""
+
+
+def clean(content):
+ return [item for item in content if not is_blank(item)]
+
+
+class Formatter:
+
+ def __init__(self, filename, stream=sys.stdout):
+ self.stream = stream
+ self.style = dict(preformat=False,
+ in_ul=False,
+ no_nl=False,
+ in_table=False,
+ in_tr=False,
+ index=[])
+ self.stack = []
+ self.strip_re = re.compile("^[ \t]+")
+ self.filename = filename
+ self.at_bol = True
+
+ def warning(self, msg):
+ sys.stderr.write(msg + '\n')
+
+ def set(self, var, val):
+ self.style[var] = val
+
+ def get(self, var):
+ return self.style[var]
+
+ def push(self, **kwargs):
+ self.stack.append(self.style.copy())
+ self.style.update(**kwargs)
+
+ def pop(self):
+ self.style = self.stack.pop()
+
+ def show(self, s):
+ self.stream.write(s)
+ if s != '':
+ self.at_bol = s.endswith('\n')
+
+ def pp_with(self, content, var, val):
+ self.push()
+ self.set(var, val)
+ self.pp(content)
+ self.pop()
+
+ def fmt(self, format, content, var=None):
+ # String.partition is only in 2.5+
+ # (pre,sep,post) = format.partition("@")
+ if self.get('no_nl') and '\n' in format:
+ self.warning("can't handle line breaks in <dt>...</dt>")
+ format = "@"
+ f = format.split('@', 1)
+ pre = f[0]
+ if len(f) > 1:
+ sep = '@'
+ post = f[1]
+ else:
+ sep = ''
+ post = ''
+
+ if pre != "":
+ self.show(pre)
+ if sep != "":
+ if var:
+ if var == 'index':
+ val = self.get('index') + [0]
+ else:
+ val = True
+ self.pp_with(content, var, val)
+ else:
+ self.pp(content)
+ if post != "":
+ self.show(post)
+
+ def pp_li(self, content):
+ if self.get('in_ul'):
+ self.fmt("\n.IP \(bu 4n\n@", content)
+ else:
+ idx = self.get('index')
+ idx[-1] += 1
+ sec = ".".join(map(str, idx))
+ self.show("\n.IP \\fB%s\\fR\n" % sec)
+ self.set('index', idx)
+ self.pp(content)
+
+ def pp_title(self):
+ self.show("\n.TH " +
+ os.path.basename(self.filename).replace(".html", "") +
+ " 1 \"\" \"GRASS " +
+ version +
+ "\" \"Grass User's Manual\"")
+
+ def pp_tr(self, content):
+ content = clean(content)
+ self.push(in_tr=True)
+ col = 0
+ for item in content:
+ if not is_tuple(item):
+ self.warning("invalid item in table row: %s" % str(item))
+ continue
+ (tag, attrs, body) = item
+ if tag not in ['td', 'th']:
+ self.warning("invalid tag in table row: %s" % tag)
+ continue
+ if col > 0:
+ self.show("\t \t")
+ self.show("T{\n")
+ self.pp(body)
+ self.show("\nT}")
+ col += 1
+ self.show("\n")
+ self.pop()
+
+ def pp_tbody(self, content):
+ for item in content:
+ if is_tuple(item):
+ (tag, attrs, body) = item
+ if tag in ['thead', 'tbody', 'tfoot']:
+ self.pp_tbody(body)
+ elif tag == 'tr':
+ self.pp_tr(body)
+ self.show(".sp 1\n")
+
+ def count_cols(self, content):
+ cols = 0
+ for item in content:
+ n = 0
+ if is_blank(item):
+ pass
+ elif is_tuple(item):
+ (tag, attrs, body) = item
+ if tag in ['thead', 'tbody', 'tfoot']:
+ n = self.count_cols(body)
+ elif tag == 'tr':
+ n = len(clean(body))
+ cols = max(cols, n)
+ else:
+ self.warning("invalid item in table: %s" % str(item))
+ return cols
+
+ def pp_table(self, content):
+ cols = self.count_cols(content)
+ if cols == 0:
+ return
+ self.show("\n.TS\nexpand;\n")
+ self.show(" lw1 ".join(["lw60" for i in range(cols)]) + ".\n")
+ self.pp_tbody(content)
+ self.show("\n.TE\n")
+
+ def pp_tag(self, tag, content):
+ if self.get('in_tr') and tag not in styles:
+ self.pp(content)
+ elif tag in formats:
+ spec = formats[tag]
+ if is_string(spec):
+ self.fmt(spec, content)
+ else:
+ (fmt, var) = spec
+ self.fmt(fmt, content, var)
+ elif tag == 'table':
+ if self.get('in_table'):
+ self.warning("cannot handle nested tables")
+ return
+ self.push(in_table=True)
+ self.pp_table(content)
+ self.pop()
+ elif tag == 'li':
+ self.pp_li(content)
+ elif tag == 'title':
+ self.pp_title()
+ else:
+ self.pp(content)
+
+ def pp_string(self, content):
+ if content == "":
+ return
+ s = content
+ if self.get('no_nl'):
+ s = s.replace("\n", " ")
+ s = s.replace("\\", "\\(rs")
+ s = s.replace("'", "\\(cq")
+ s = s.replace("\"", "\\(dq")
+ s = s.replace("`", "\\(ga")
+ s = s.replace("-", "\\-")
+ if self.at_bol and s[0] in [".", "'"]:
+ s = "\\&" + s
+ self.show(s)
+
+ def pp_text(self, content):
+ if content == "":
+ return
+ lines = content.splitlines(True)
+ if len(lines) != 1:
+ for line in lines:
+ self.pp_text(line)
+ return
+ else:
+ content = lines[0]
+ if self.at_bol and not self.get('preformat'):
+ content = self.strip_re.sub('', content)
+ self.pp_string(content)
+
+ def pp_list(self, content):
+ for item in content:
+ self.pp(item)
+
+ def pp(self, content):
+ if is_list(content):
+ self.pp_list(content)
+ elif is_tuple(content):
+ (tag, attrs, body) = content
+ self.pp_tag(tag, body)
+ elif is_string(content):
+ self.pp_text(content)
Copied: grass/trunk/tools/g.html2man/ghtml.py (from rev 70284, grass/trunk/tools/g.html2man/html.py)
===================================================================
--- grass/trunk/tools/g.html2man/ghtml.py (rev 0)
+++ grass/trunk/tools/g.html2man/ghtml.py 2017-01-06 19:40:09 UTC (rev 70285)
@@ -0,0 +1,235 @@
+from __future__ import (absolute_import, division, generators, nested_scopes,
+ print_function, unicode_literals, with_statement)
+import sys
+
+try:
+ # Python 2 import
+ import HTMLParser as base
+ HTMLParseError = base.HTMLParseError
+except:
+ # Python 3 import
+ import html.parser as base
+ # TODO: this needs a better fix since HTMLParseError is actually
+ # used including its attributes, so that actually fails
+ # HTMLParseError is depreciated, parsing is not strict
+ HTMLParseError = Exception
+
+try:
+ # Python 3
+ from html.entities import entitydefs
+except ImportError:
+ # Python 2
+ from htmlentitydefs import entitydefs
+
+
+__all__ = ["HTMLParser", "HTMLParseError"]
+
+omit_start = ["body", "tbody", "head", "html"]
+
+single = ["area", "base", "basefont", "br", "col", "frame",
+ "hr", "img", "input", "isindex", "link", "meta", "param"]
+single = frozenset(single)
+
+heading = ["h1", "h2", "h3", "h4", "h5", "h6"]
+fontstyle = ["tt", "i", "b", "u", "s", "strike", "big", "small"]
+phrase = ["em", "strong", "dfn", "code", "samp", "kbd", "var", "cite", "abbr",
+ "acronym"]
+special = ["a", "img", "applet", "object", "font", "basefont", "br", "script",
+ "map", "q", "sub", "sup", "span", "bdo", "iframe"]
+formctrl = ["input", "select", "textarea", "label", "button"]
+lists = ["ul", "ol", " dir", "menu"]
+head_misc = ["script", "style", "meta", "link", "object"]
+pre_exclusion = ["img", "object", "applet", "big", "small", "sub", "sup",
+ "font", "basefont"]
+block = ["p", "pre", "dl", "div", "center", "noscript", "noframes",
+ "blockquote", "form", "isindex", "hr", "table", "fieldset",
+ "address"] + heading + lists
+inline = fontstyle + phrase + special + formctrl
+flow = block + inline
+html_content = ["head", "body"]
+head_content = ["title", "isindex", "base"]
+
+
+def setify(d):
+ return dict([(key, frozenset(val)) for key, val in d.items()])
+
+
+def omit(allowed, tags):
+ result = {}
+ for k, v in allowed.items():
+ for t in tags:
+ if t in v:
+ v = v.union(allowed[t])
+ result[k] = v
+ return result
+
+allowed = {
+ "a": inline,
+ "abbr": inline,
+ "acronym": inline,
+ "address": inline + ["p"],
+ "applet": flow + ["param"],
+ "b": inline,
+ "bdo": inline,
+ "big": inline,
+ "blockquote": flow,
+ "body": flow + ["ins", "del"],
+ "button": flow,
+ "caption": inline,
+ "center": flow,
+ "cite": inline,
+ "code": inline,
+ "colgroup": ["col"],
+ "dd": flow,
+ "del": flow,
+ "dfn": inline,
+ "dir": ["li"],
+ "div": flow,
+ "dl": ["dt", "dd"],
+ "dt": inline,
+ "em": inline,
+ "fieldset": flow + ["legend"],
+ "font": inline,
+ "form": flow,
+ "frameset": ["frameset", "frame", "noframes"],
+ "h1": inline,
+ "h2": inline,
+ "h3": inline,
+ "h4": inline,
+ "h5": inline,
+ "h6": inline,
+ "head": head_content + head_misc,
+ "html": html_content,
+ "i": inline,
+ "iframe": flow,
+ "ins": flow,
+ "kbd": inline,
+ "label": inline,
+ "legend": inline,
+ "li": flow,
+ "map": block + ["area"],
+ "menu": ["li"],
+ "noframes": flow,
+ "noscript": flow,
+ "object": flow + ["param"],
+ "ol": ["li"],
+ "optgroup": ["option"],
+ "option": [],
+ "p": inline,
+ "pre": inline,
+ "q": inline,
+ "s": inline,
+ "samp": inline,
+ "script": [],
+ "select": ["optgroup", "option"],
+ "small": inline,
+ "span": inline,
+ "strike": inline,
+ "strong": inline,
+ "style": [],
+ "sub": inline,
+ "sup": inline,
+ "table": ["caption", "col", "colgroup", "thead", "tfoot", "tbody"],
+ "tbody": ["tr"],
+ "td": flow,
+ "textarea": [],
+ "tfoot": ["tr"],
+ "th": flow,
+ "thead": ["tr"],
+ "title": [],
+ "tr": ["th", "td"],
+ "tt": inline,
+ "u": inline,
+ "ul": ["li"],
+ "var": inline
+}
+
+allowed = setify(allowed)
+allowed = omit(allowed, omit_start)
+
+excluded = {
+ "a": ["a"],
+ "button": formctrl + ["a", "form", "isindex", "fieldset", "iframe"],
+ "dir": block,
+ "form": ["form"],
+ "label": ["label"],
+ "menu": block,
+ "pre": pre_exclusion
+}
+
+excluded = setify(excluded)
+
+
+class HTMLParser(base.HTMLParser):
+
+ def __init__(self, entities=None):
+ base.HTMLParser.__init__(self)
+ self.tag_stack = []
+ self.excluded = frozenset()
+ self.excluded_stack = []
+ self.data = []
+ self.data_stack = []
+ self.decls = []
+ if entities:
+ self.entities = entities
+ else:
+ self.entities = {}
+
+ def top(self):
+ if self.tag_stack == []:
+ return None
+ else:
+ return self.tag_stack[-1][0]
+
+ def pop(self):
+ self.excluded = self.excluded_stack.pop()
+ data = self.data
+ self.data = self.data_stack.pop()
+ (tag, attrs) = self.tag_stack.pop()
+ self.append((tag, attrs, data))
+ return tag
+
+ def push(self, tag, attrs):
+ self.tag_stack.append((tag, attrs))
+ self.excluded_stack.append(self.excluded)
+ if tag in excluded:
+ self.excluded = self.excluded.union(excluded[tag])
+ self.data_stack.append(self.data)
+ self.data = []
+
+ def append(self, item):
+ self.data.append(item)
+
+ def is_allowed(self, tag):
+ return tag not in self.excluded and tag in allowed[self.top()]
+
+ def handle_starttag(self, tag, attrs):
+ if self.tag_stack != []:
+ while not self.is_allowed(tag):
+ self.pop()
+ if tag not in single:
+ self.push(tag, attrs)
+ else:
+ self.append((tag, attrs, None))
+
+ def handle_entityref(self, name):
+ if name in self.entities:
+ self.handle_data(self.entities[name])
+ elif name in entitydefs:
+ self.handle_data(entitydefs[name])
+ else:
+ sys.stderr.write("unrecognized entity: %s\n" % name)
+
+ def handle_charref(self, name):
+ sys.stderr.write('unsupported character reference <%s>' % name)
+
+ def handle_data(self, data):
+ self.append(data)
+
+ def handle_endtag(self, tag):
+ while True:
+ if self.pop() == tag:
+ break
+
+ def handle_decl(self, decl):
+ self.decls.append(decl)
Deleted: grass/trunk/tools/g.html2man/groff.py
===================================================================
--- grass/trunk/tools/g.html2man/groff.py 2017-01-06 18:59:14 UTC (rev 70284)
+++ grass/trunk/tools/g.html2man/groff.py 2017-01-06 19:40:09 UTC (rev 70285)
@@ -1,271 +0,0 @@
-
-import sys
-import os
-import re
-
-__all__ = ["Formatter"]
-
-try:
- version = os.environ['VERSION_NUMBER']
-except:
- version = ""
-
-styles = {
- 'b': "\\fB@\\fR",
- 'i': "\\fI@\\fR",
- 'em': "\\fI@\\fR",
- 'code': "\\fC@\\fR",
- 'span': "\\fC@\\fR",
- 'sup': "\\u@\\d",
- 'hr': ""
-}
-
-formats = {
- 'br': "\n.br\n",
- 'h2': "\n.SH @",
- 'h3': "\n.SS @",
- 'h4': "\n.SS @",
- 'dt': ("\n.IP \"@\" 4m", 'no_nl'),
- 'dd': "\n.br\n@",
- 'ul': ("\n.RS 4n\n@\n.RE\n", 'in_ul'),
- 'menu': ("\n.RS 4n\n@\n.RE\n", 'in_ul'),
- 'dir': ("\n.RS 4n\n@\n.RE\n", 'in_ul'),
- 'ol': ("\n.IP\n@\n.PP\n", 'index'),
- 'p': "\n.PP\n@",
- 'pre': ("\n.br\n.nf\n\\fC\n@\n\\fR\n.fi\n", 'preformat')
-}
-
-formats.update(styles)
-
-
-def is_string(x):
- return isinstance(x, str)
-
-
-def is_tuple(x):
- return isinstance(x, tuple)
-
-
-def is_list(x):
- return isinstance(x, list)
-
-
-def is_blank(s):
- return is_string(s) and s.strip() == ""
-
-
-def clean(content):
- return [item for item in content if not is_blank(item)]
-
-
-class Formatter:
-
- def __init__(self, filename, stream=sys.stdout):
- self.stream = stream
- self.style = dict(preformat=False,
- in_ul=False,
- no_nl=False,
- in_table=False,
- in_tr=False,
- index=[])
- self.stack = []
- self.strip_re = re.compile("^[ \t]+")
- self.filename = filename
- self.at_bol = True
-
- def warning(self, msg):
- sys.stderr.write(msg + '\n')
-
- def set(self, var, val):
- self.style[var] = val
-
- def get(self, var):
- return self.style[var]
-
- def push(self, **kwargs):
- self.stack.append(self.style.copy())
- self.style.update(**kwargs)
-
- def pop(self):
- self.style = self.stack.pop()
-
- def show(self, s):
- self.stream.write(s)
- if s != '':
- self.at_bol = s.endswith('\n')
-
- def pp_with(self, content, var, val):
- self.push()
- self.set(var, val)
- self.pp(content)
- self.pop()
-
- def fmt(self, format, content, var=None):
- # String.partition is only in 2.5+
- # (pre,sep,post) = format.partition("@")
- if self.get('no_nl') and '\n' in format:
- self.warning("can't handle line breaks in <dt>...</dt>")
- format = "@"
- f = format.split('@', 1)
- pre = f[0]
- if len(f) > 1:
- sep = '@'
- post = f[1]
- else:
- sep = ''
- post = ''
-
- if pre != "":
- self.show(pre)
- if sep != "":
- if var:
- if var == 'index':
- val = self.get('index') + [0]
- else:
- val = True
- self.pp_with(content, var, val)
- else:
- self.pp(content)
- if post != "":
- self.show(post)
-
- def pp_li(self, content):
- if self.get('in_ul'):
- self.fmt("\n.IP \(bu 4n\n@", content)
- else:
- idx = self.get('index')
- idx[-1] += 1
- sec = ".".join(map(str, idx))
- self.show("\n.IP \\fB%s\\fR\n" % sec)
- self.set('index', idx)
- self.pp(content)
-
- def pp_title(self):
- self.show("\n.TH " +
- os.path.basename(self.filename).replace(".html", "") +
- " 1 \"\" \"GRASS " +
- version +
- "\" \"Grass User's Manual\"")
-
- def pp_tr(self, content):
- content = clean(content)
- self.push(in_tr=True)
- col = 0
- for item in content:
- if not is_tuple(item):
- self.warning("invalid item in table row: %s" % str(item))
- continue
- (tag, attrs, body) = item
- if tag not in ['td', 'th']:
- self.warning("invalid tag in table row: %s" % tag)
- continue
- if col > 0:
- self.show("\t \t")
- self.show("T{\n")
- self.pp(body)
- self.show("\nT}")
- col += 1
- self.show("\n")
- self.pop()
-
- def pp_tbody(self, content):
- for item in content:
- if is_tuple(item):
- (tag, attrs, body) = item
- if tag in ['thead', 'tbody', 'tfoot']:
- self.pp_tbody(body)
- elif tag == 'tr':
- self.pp_tr(body)
- self.show(".sp 1\n")
-
- def count_cols(self, content):
- cols = 0
- for item in content:
- n = 0
- if is_blank(item):
- pass
- elif is_tuple(item):
- (tag, attrs, body) = item
- if tag in ['thead', 'tbody', 'tfoot']:
- n = self.count_cols(body)
- elif tag == 'tr':
- n = len(clean(body))
- cols = max(cols, n)
- else:
- self.warning("invalid item in table: %s" % str(item))
- return cols
-
- def pp_table(self, content):
- cols = self.count_cols(content)
- if cols == 0:
- return
- self.show("\n.TS\nexpand;\n")
- self.show(" lw1 ".join(["lw60" for i in range(cols)]) + ".\n")
- self.pp_tbody(content)
- self.show("\n.TE\n")
-
- def pp_tag(self, tag, content):
- if self.get('in_tr') and tag not in styles:
- self.pp(content)
- elif tag in formats:
- spec = formats[tag]
- if is_string(spec):
- self.fmt(spec, content)
- else:
- (fmt, var) = spec
- self.fmt(fmt, content, var)
- elif tag == 'table':
- if self.get('in_table'):
- self.warning("cannot handle nested tables")
- return
- self.push(in_table=True)
- self.pp_table(content)
- self.pop()
- elif tag == 'li':
- self.pp_li(content)
- elif tag == 'title':
- self.pp_title()
- else:
- self.pp(content)
-
- def pp_string(self, content):
- if content == "":
- return
- s = content
- if self.get('no_nl'):
- s = s.replace("\n", " ")
- s = s.replace("\\", "\\(rs")
- s = s.replace("'", "\\(cq")
- s = s.replace("\"", "\\(dq")
- s = s.replace("`", "\\(ga")
- s = s.replace("-", "\\-")
- if self.at_bol and s[0] in [".", "'"]:
- s = "\\&" + s
- self.show(s)
-
- def pp_text(self, content):
- if content == "":
- return
- lines = content.splitlines(True)
- if len(lines) != 1:
- for line in lines:
- self.pp_text(line)
- return
- else:
- content = lines[0]
- if self.at_bol and not self.get('preformat'):
- content = self.strip_re.sub('', content)
- self.pp_string(content)
-
- def pp_list(self, content):
- for item in content:
- self.pp(item)
-
- def pp(self, content):
- if is_list(content):
- self.pp_list(content)
- elif is_tuple(content):
- (tag, attrs, body) = content
- self.pp_tag(tag, body)
- elif is_string(content):
- self.pp_text(content)
Deleted: grass/trunk/tools/g.html2man/html.py
===================================================================
--- grass/trunk/tools/g.html2man/html.py 2017-01-06 18:59:14 UTC (rev 70284)
+++ grass/trunk/tools/g.html2man/html.py 2017-01-06 19:40:09 UTC (rev 70285)
@@ -1,219 +0,0 @@
-from __future__ import (absolute_import, division, generators, nested_scopes,
- print_function, unicode_literals, with_statement)
-import sys
-import HTMLParser as base
-import htmlentitydefs
-
-HTMLParseError = base.HTMLParseError
-
-__all__ = ["HTMLParser", "HTMLParseError"]
-
-omit_start = ["body", "tbody", "head", "html"]
-
-single = ["area", "base", "basefont", "br", "col", "frame",
- "hr", "img", "input", "isindex", "link", "meta", "param"]
-single = frozenset(single)
-
-heading = ["h1", "h2", "h3", "h4", "h5", "h6"]
-fontstyle = ["tt", "i", "b", "u", "s", "strike", "big", "small"]
-phrase = ["em", "strong", "dfn", "code", "samp", "kbd", "var", "cite", "abbr",
- "acronym"]
-special = ["a", "img", "applet", "object", "font", "basefont", "br", "script",
- "map", "q", "sub", "sup", "span", "bdo", "iframe"]
-formctrl = ["input", "select", "textarea", "label", "button"]
-lists = ["ul", "ol", " dir", "menu"]
-head_misc = ["script", "style", "meta", "link", "object"]
-pre_exclusion = ["img", "object", "applet", "big", "small", "sub", "sup",
- "font", "basefont"]
-block = ["p", "pre", "dl", "div", "center", "noscript", "noframes",
- "blockquote", "form", "isindex", "hr", "table", "fieldset",
- "address"] + heading + lists
-inline = fontstyle + phrase + special + formctrl
-flow = block + inline
-html_content = ["head", "body"]
-head_content = ["title", "isindex", "base"]
-
-
-def setify(d):
- return dict([(key, frozenset(val)) for key, val in d.iteritems()])
-
-
-def omit(allowed, tags):
- result = {}
- for k, v in allowed.iteritems():
- for t in tags:
- if t in v:
- v = v.union(allowed[t])
- result[k] = v
- return result
-
-allowed = {
- "a": inline,
- "abbr": inline,
- "acronym": inline,
- "address": inline + ["p"],
- "applet": flow + ["param"],
- "b": inline,
- "bdo": inline,
- "big": inline,
- "blockquote": flow,
- "body": flow + ["ins", "del"],
- "button": flow,
- "caption": inline,
- "center": flow,
- "cite": inline,
- "code": inline,
- "colgroup": ["col"],
- "dd": flow,
- "del": flow,
- "dfn": inline,
- "dir": ["li"],
- "div": flow,
- "dl": ["dt", "dd"],
- "dt": inline,
- "em": inline,
- "fieldset": flow + ["legend"],
- "font": inline,
- "form": flow,
- "frameset": ["frameset", "frame", "noframes"],
- "h1": inline,
- "h2": inline,
- "h3": inline,
- "h4": inline,
- "h5": inline,
- "h6": inline,
- "head": head_content + head_misc,
- "html": html_content,
- "i": inline,
- "iframe": flow,
- "ins": flow,
- "kbd": inline,
- "label": inline,
- "legend": inline,
- "li": flow,
- "map": block + ["area"],
- "menu": ["li"],
- "noframes": flow,
- "noscript": flow,
- "object": flow + ["param"],
- "ol": ["li"],
- "optgroup": ["option"],
- "option": [],
- "p": inline,
- "pre": inline,
- "q": inline,
- "s": inline,
- "samp": inline,
- "script": [],
- "select": ["optgroup", "option"],
- "small": inline,
- "span": inline,
- "strike": inline,
- "strong": inline,
- "style": [],
- "sub": inline,
- "sup": inline,
- "table": ["caption", "col", "colgroup", "thead", "tfoot", "tbody"],
- "tbody": ["tr"],
- "td": flow,
- "textarea": [],
- "tfoot": ["tr"],
- "th": flow,
- "thead": ["tr"],
- "title": [],
- "tr": ["th", "td"],
- "tt": inline,
- "u": inline,
- "ul": ["li"],
- "var": inline
-}
-
-allowed = setify(allowed)
-allowed = omit(allowed, omit_start)
-
-excluded = {
- "a": ["a"],
- "button": formctrl + ["a", "form", "isindex", "fieldset", "iframe"],
- "dir": block,
- "form": ["form"],
- "label": ["label"],
- "menu": block,
- "pre": pre_exclusion
-}
-
-excluded = setify(excluded)
-
-
-class HTMLParser(base.HTMLParser):
-
- def __init__(self, entities=None):
- base.HTMLParser.__init__(self)
- self.tag_stack = []
- self.excluded = frozenset()
- self.excluded_stack = []
- self.data = []
- self.data_stack = []
- self.decls = []
- if entities:
- self.entities = entities
- else:
- self.entities = {}
-
- def top(self):
- if self.tag_stack == []:
- return None
- else:
- return self.tag_stack[-1][0]
-
- def pop(self):
- self.excluded = self.excluded_stack.pop()
- data = self.data
- self.data = self.data_stack.pop()
- (tag, attrs) = self.tag_stack.pop()
- self.append((tag, attrs, data))
- return tag
-
- def push(self, tag, attrs):
- self.tag_stack.append((tag, attrs))
- self.excluded_stack.append(self.excluded)
- if tag in excluded:
- self.excluded = self.excluded.union(excluded[tag])
- self.data_stack.append(self.data)
- self.data = []
-
- def append(self, item):
- self.data.append(item)
-
- def is_allowed(self, tag):
- return tag not in self.excluded and tag in allowed[self.top()]
-
- def handle_starttag(self, tag, attrs):
- if self.tag_stack != []:
- while not self.is_allowed(tag):
- self.pop()
- if tag not in single:
- self.push(tag, attrs)
- else:
- self.append((tag, attrs, None))
-
- def handle_entityref(self, name):
- if name in self.entities:
- self.handle_data(self.entities[name])
- elif name in htmlentitydefs.entitydefs:
- self.handle_data(htmlentitydefs.entitydefs[name])
- else:
- sys.stderr.write("unrecognized entity: %s\n" % name)
-
- def handle_charref(self, name):
- sys.stderr.write('unsupported character reference <%s>' % name)
-
- def handle_data(self, data):
- self.append(data)
-
- def handle_endtag(self, tag):
- while True:
- if self.pop() == tag:
- break
-
- def handle_decl(self, decl):
- self.decls.append(decl)
More information about the grass-commit
mailing list