import os, sys, re, string, glob
+verbose = False
+show_warnings = True
+show_errors = True
class DeclarationParser(object):
def __init__(self, line=None):
try:
self.parse_section(module_name, section_name, file_name, lineno, lines)
except AssertionError, args:
- print "RST parser error: assertion in \"%s\" File: %s (line %s)" % (section_name, file_name, lineno)
- print " Details: %s" % args
+ if show_errors:
+ print >> sys.stderr, "RST parser error: assertion in \"%s\" File: %s (line %s)" % (section_name, file_name, lineno)
+ print >> sys.stderr, " Details: %s" % args
def parse_section(self, module_name, section_name, file_name, lineno, lines):
self.sections_total += 1
# skip sections having whitespace in name
if section_name.find(" ") >= 0 and section_name.find("::operator") < 0:
- print "SKIPPED: \"%s\" File: %s (line %s)" % (section_name, file_name, lineno)
+ if show_errors:
+ print "SKIPPED: \"%s\" File: %s (line %s)" % (section_name, file_name, lineno)
self.sections_skipped += 1
return
else:
capturing_seealso = False
- # continue param parsing
- if pdecl.active:
- pdecl.append(l)
- if pdecl.active:
- continue
- else:
- self.add_new_pdecl(func, pdecl)
- # do not continue - current line can contain next parameter definition
-
ll = l.strip()
if ll == "..":
expected_brief = False
else:
skip_code_lines = False
- if ll.startswith(".. code-block::") or ll.startswith(".. math::") or ll.startswith(".. image::"):
+ if ll.startswith(".. code-block::") or ll.startswith(".. image::"):
+ #or ll.startswith(".. math::") or ll.startswith(".. image::"):
skip_code_lines = True
continue
-
+
# todo: parse structure members; skip them for now
if ll.startswith(".. ocv:member::"):
skip_code_lines = True
continue
+
+ #ignore references (todo: collect them)
+ if l.startswith(".. ["):
+ continue
if ll.startswith(".. "):
expected_brief = False
# turn on line-skipping mode for code fragments
skip_code_lines = True
ll = ll[:len(ll)-2]
+
+ # continue param parsing (process params after processing .. at the beginning of the line and :: at the end)
+ if pdecl.active:
+ pdecl.append(l)
+ if pdecl.active:
+ continue
+ else:
+ self.add_new_pdecl(func, pdecl)
+ # do not continue - current line can contain next parameter definition
# parse ".. seealso::" blocks
if ll.startswith(".. seealso::"):
# endfor l in lines
if fdecl.balance != 0:
- print "RST parser error: invalid parentheses balance in \"%s\" File: %s (line %s)" % (section_name, file_name, lineno)
+ if show_errors:
+ print >> sys.stderr, "RST parser error: invalid parentheses balance in \"%s\" File: %s (line %s)" % (section_name, file_name, lineno)
+ return
# save last parameter if needed
if pdecl.active:
if self.validate(func):
self.definitions[func["name"]] = func
self.sections_parsed += 1
- #self.print_info(func)
+ if verbose:
+ self.print_info(func)
elif func:
- self.print_info(func, True)
- pass
+ if show_errors:
+ self.print_info(func, True, sys.stderr)
def parse_rst_file(self, module_name, doc):
doc = os.path.abspath(doc)
# handle tabs
if l.find("\t") >= 0:
whitespace_warnings += 1
- if whitespace_warnings <= max_whitespace_warnings:
- print "RST parser warning: tab symbol instead of space is used at file %s (line %s)" % (doc, lineno)
+ if whitespace_warnings <= max_whitespace_warnings and show_warnings:
+ print >> sys.stderr, "RST parser warning: tab symbol instead of space is used at file %s (line %s)" % (doc, lineno)
l = l.replace("\t", " ")
# handle first line
def add_new_pdecl(self, func, decl):
params = func.get("params",{})
if decl.name in params:
- print "RST parser error: redefinition of parameter \"%s\" in \"%s\" File: %s (line %s)" \
- % (decl.name, func["name"], func["file"], func["line"])
+ if show_errors:
+ print >> sys.stderr, "RST parser error: redefinition of parameter \"%s\" in \"%s\" File: %s (line %s)" \
+ % (decl.name, func["name"], func["file"], func["line"])
else:
params[decl.name] = decl.comment
func["params"] = params
- def print_info(self, func, skipped=False):
- print
+ def print_info(self, func, skipped=False, out = sys.stdout):
+ print >> out
if skipped:
- print "SKIPPED DEFINITION:"
- print "name: %s" % (func.get("name","~empty~"))
- print "file: %s (line %s)" % (func.get("file","~empty~"), func.get("line","~empty~"))
- print "is class: %s" % func.get("isclass",False)
- print "is struct: %s" % func.get("isstruct",False)
- print "module: %s" % func.get("module","~unknown~")
- print "namespace: %s" % func.get("namespace", "~empty~")
- print "class: %s" % (func.get("class","~empty~"))
- print "method: %s" % (func.get("method","~empty~"))
- print "brief: %s" % (func.get("brief","~empty~"))
+ print >> out, "SKIPPED DEFINITION:"
+ print >> out, "name: %s" % (func.get("name","~empty~"))
+ print >> out, "file: %s (line %s)" % (func.get("file","~empty~"), func.get("line","~empty~"))
+ print >> out, "is class: %s" % func.get("isclass",False)
+ print >> out, "is struct: %s" % func.get("isstruct",False)
+ print >> out, "module: %s" % func.get("module","~unknown~")
+ print >> out, "namespace: %s" % func.get("namespace", "~empty~")
+ print >> out, "class: %s" % (func.get("class","~empty~"))
+ print >> out, "method: %s" % (func.get("method","~empty~"))
+ print >> out, "brief: %s" % (func.get("brief","~empty~"))
if "decls" in func:
- print "declarations:"
+ print >> out, "declarations:"
for d in func["decls"]:
- print " %7s: %s" % (d[0], re.sub(r"[ ]+", " ", d[1]))
+ print >> out, " %7s: %s" % (d[0], re.sub(r"[ ]+", " ", d[1]))
if "seealso" in func:
- print "seealso: ", func["seealso"]
+ print >> out, "seealso: ", func["seealso"]
if "params" in func:
- print "parameters:"
+ print >> out, "parameters:"
for name, comment in func["params"].items():
- print "%23s: %s" % (name, comment)
- if not skipped:
- print "long: %s" % (func.get("long","~empty~"))
- print
+ print >> out, "%23s: %s" % (name, comment)
+ print >> out, "long: %s" % (func.get("long","~empty~"))
+ print >> out
def validate(self, func):
if func.get("decls",None) is None:
- if not func.get("isclass",False) and not func.get("isstruct",False):
- return False
+ if not func.get("isclass",False) and not func.get("isstruct",False):
+ return False
if func["name"] in self.definitions:
- print "RST parser error: \"%s\" from file: %s (line %s) is already documented in file: %s (line %s)" \
- % (func["name"], func["file"], func["line"], self.definitions[func["name"]]["file"], self.definitions[func["name"]]["line"])
- return False
+ if show_errors:
+ print >> sys.stderr, "RST parser error: \"%s\" from file: %s (line %s) is already documented in file: %s (line %s)" \
+ % (func["name"], func["file"], func["line"], self.definitions[func["name"]]["file"], self.definitions[func["name"]]["line"])
+ return False
return self.validateParams(func)
def validateParams(self, func):
# 1. all params are documented
for p in params:
- if p not in documentedParams:
- print "RST parser warning: parameter \"%s\" of \"%s\" is undocumented. File: %s (line %s)" % (p, func["name"], func["file"], func["line"])
+ if p not in documentedParams and show_warnings:
+ print >> sys.stderr, "RST parser warning: parameter \"%s\" of \"%s\" is undocumented. File: %s (line %s)" % (p, func["name"], func["file"], func["line"])
# 2. only real params are documented
for p in documentedParams:
- if p not in params:
- print "RST parser warning: unexisting parameter \"%s\" of \"%s\" is documented. File: %s (line %s)" % (p, func["name"], func["file"], func["line"])
+ if p not in params and show_warnings:
+ print >> sys.stderr, "RST parser warning: unexisting parameter \"%s\" of \"%s\" is documented. File: %s (line %s)" % (p, func["name"], func["file"], func["line"])
return True
def normalize(self, func):
if fname[6:] == func.get("name", ""):
func["name"] = fname[4:]
func["method"] = fname[4:]
- else:
- print "RST parser warning: invalid definition of old C function \"%s\" - section name is \"%s\" instead of \"%s\". File: %s (line %s)" % (fname, func["name"], fname[6:], func["file"], func["line"])
+ elif show_warnings:
+ print >> sys.stderr, "RST parser warning: invalid definition of old C function \"%s\" - section name is \"%s\" instead of \"%s\". File: %s (line %s)" % (fname, func["name"], fname[6:], func["file"], func["line"])
#self.print_info(func)
-
+
def normalizeText(self, s):
if s is None:
return s
+ s = re.sub(r"\.\. math::[ ]*\n+(.*?)(\n[ ]*\n|$)", mathReplace2, s)
+ s = re.sub(r":math:`([^`]+?)`", mathReplace, s)
+ s = re.sub(r" *:sup:", "^", s)
+
+ s = s.replace(":ocv:class:", "")
+ s = s.replace(":ocv:struct:", "")
+ s = s.replace(":ocv:func:", "")
+ s = s.replace(":ocv:cfunc:","")
+ s = s.replace(":c:type:", "")
+ s = s.replace(":c:func:", "")
+ s = s.replace(":ref:", "")
+ s = s.replace(":math:", "")
+ s = s.replace(":func:", "")
+
+ s = s.replace("]_", "]")
+ s = s.replace(".. note::", "Note:")
+ s = s.replace(".. table::", "")
+ s = s.replace(".. ocv:function::", "")
+ s = s.replace(".. ocv:cfunction::", "")
+
+ # remove ".. identifier:" lines
+ s = re.sub(r"(^|\n)\.\. [a-zA-Z_0-9]+(::[a-zA-Z_0-9]+)?:(\n|$)", "\n ", s)
+ # unwrap urls
+ s = re.sub(r"`([^`<]+ )<(https?://[^>]+)>`_", "\\1(\\2)", s)
+ # remove tailing ::
+ s = re.sub(r"::(\n|$)", "\\1", s)
+
# normalize line endings
s = re.sub(r"\r\n", "\n", s)
# remove extra line breaks before/after _ or ,
s = re.sub(r"\n[ ]*([_,])\n", r"\1 ", s)
# remove extra line breaks after `
#s = re.sub(r"`\n", "` ", s)
- # remove extra space after ( and before )
+ # remove extra space after ( and before .,)
s = re.sub(r"\([\n ]+", "(", s)
- s = re.sub(r"[\n ]+\)", ")", s)
+ s = re.sub(r"[\n ]+(\.|,|\))", "\\1", s)
# remove extra line breaks after ".. note::"
s = re.sub(r"\.\. note::\n+", ".. note:: ", s)
# remove extra line breaks before *
- s = re.sub(r"\n\n\*", "\n*", s)
+ s = re.sub(r"\n+\*", "\n*", s)
# remove extra line breaks after *
s = re.sub(r"\n\*\n+", "\n* ", s)
# remove extra line breaks before #.
- s = re.sub(r"\n\n#\.", "\n#.", s)
+ s = re.sub(r"\n+#\.", "\n#.", s)
# remove extra line breaks after #.
s = re.sub(r"\n#\.\n+", "\n#. ", s)
# remove extra line breaks before `
# remove trailing whitespaces
s = re.sub(r"[ ]+$", "", s)
# remove .. for references
- s = re.sub(r"\.\. \[", "[", s)
+ #s = re.sub(r"\.\. \[", "[", s)
# unescape
s = re.sub(r"\\(.)", "\\1", s)
- s = s.replace(":ocv:class:", "")
- s = s.replace(":ocv:struct:", "")
- s = s.replace(":ocv:func:", "")
- s = s.replace(":ocv:cfunc:","")
- s = s.replace(":c:type:", "")
- s = s.replace(":c:func:", "")
- s = s.replace(":ref:", "")
- s = s.replace(":math:", "")
- s = s.replace(":func:", "")
-
- s = s.replace("]_", "]")
- s = s.replace(".. note::", "Note:")
- s = s.replace(".. table::", "")
- s = s.replace(".. ocv:function::", "")
- s = s.replace(".. ocv:cfunction::", "")
-
- # remove ".. identifier:" lines
- s = re.sub(r"(^|\n)\.\. [a-zA-Z_0-9]+(::[a-zA-Z_0-9]+)?:(\n|$)", "\n ", s)
- # unwrap urls
- s = re.sub(r"`([^`<]+ )<(https?://[^>]+)>`_", "\\1(\\2)", s)
- # remove tailing ::
- s = re.sub(r"::$", "\n", s)
-
# remove whitespace before .
s = re.sub(r"[ ]+\.", ".", s)
# remove tailing whitespace
# compress line breaks
s = re.sub(r"\n\n+", "\n\n", s)
# remove other newlines
- s = re.sub(r"([^.\n\\=])\n([^*#\n])", "\\1 \\2", s)
+ s = re.sub(r"([^.\n\\=])\n([^*#\n]|\*[^ ])", "\\1 \\2", s)
# compress whitespace
s = re.sub(r" +", " ", s)
+ # restore math
+ s = re.sub(r" *<BR> *","\n", s)
+
# remove extra space before .
s = re.sub(r"[\n ]+\.", ".", s)
s = s.strip()
return s
+
+ def printSummary(self):
+ print
+ print "RST Parser Summary:"
+ print " Total sections: %s" % self.sections_total
+ print " Skipped sections: %s" % self.sections_skipped
+ print " Parsed sections: %s" % self.sections_parsed
+ print " Invalid sections: %s" % (self.sections_total - self.sections_parsed - self.sections_skipped)
+
+ # statistic by language
+ stat = {}
+ classes = 0
+ structs = 0
+ for name, d in self.definitions.items():
+ if d.get("isclass", False):
+ classes += 1
+ elif d.get("isstruct", False):
+ structs += 1
+ else:
+ for decl in d.get("decls",[]):
+ stat[decl[0]] = stat.get(decl[0],0) + 1
+
+ print
+ print " classes documented: %s" % classes
+ print " structs documented: %s" % structs
+ for lang in sorted(stat.items()):
+ print " %7s functions documented: %s" % lang
+
+def mathReplace2(match):
+ m = mathReplace(match)
+ #print "%s ===> %s" % (match.group(0), m)
+ return "\n\n"+m+"<BR><BR>"
+
+def hdotsforReplace(match):
+ return '... '*int(match.group(1))
+
+def matrixReplace(match):
+ m = match.group(2)
+ m = re.sub(r" *& *", " ", m)
+ return m
+
+def mathReplace(match):
+ m = match.group(1)
+
+ m = m.replace("\n", "<BR>")
+ m = re.sub(r"\\text(tt|rm)?{(.*?)}", "\\2", m)
+ m = re.sub(r"\\mbox{(.*?)}", "\\1", m)
+ m = re.sub(r"\\mathrm{(.*?)}", "\\1", m)
+ m = re.sub(r"\\vecthree{(.*?)}{(.*?)}{(.*?)}", "[\\1 \\2 \\3]", m)
+ m = re.sub(r"\\bar{(.*?)}", "\\1`", m)
+ m = re.sub(r"\\sqrt\[(\d)*\]{(.*?)}", "sqrt\\1(\\2)", m)
+ m = re.sub(r"\\sqrt{(.*?)}", "sqrt(\\1)", m)
+ m = re.sub(r"\\frac{(.*?)}{(.*?)}", "(\\1)/(\\2)", m)
+ m = re.sub(r"\\fork{(.*?)}{(.*?)}{(.*?)}{(.*?)}", "\\1 \\2; \\3 \\4", m)
+ m = re.sub(r"\\forkthree{(.*?)}{(.*?)}{(.*?)}{(.*?)}{(.*?)}{(.*?)}", "\\1 \\2; \\3 \\4; \\5 \\6", m)
+ m = re.sub(r"\\stackrel{(.*?)}{(.*?)}", "\\1 \\2", m)
+ m = re.sub(r"\\sum _{(.*?)}", "sum{by: \\1}", m)
+
+ m = re.sub(r" +", " ", m)
+ m = re.sub(r"\\begin{(?P<gtype>array|bmatrix)}(?:{[\|lcr\. ]+})? *(.*?)\\end{(?P=gtype)}", matrixReplace, m)
+ m = re.sub(r"\\hdotsfor{(\d+)}", hdotsforReplace, m)
+ m = re.sub(r"\\vecthreethree{(.*?)}{(.*?)}{(.*?)}{(.*?)}{(.*?)}{(.*?)}{(.*?)}{(.*?)}{(.*?)}", "<BR>|\\1 \\2 \\3|<BR>|\\4 \\5 \\6|<BR>|\\7 \\8 \\9|<BR>", m)
+
+ m = re.sub(r"\\left[ ]*\\lfloor[ ]*", "[", m)
+ m = re.sub(r"[ ]*\\right[ ]*\\rfloor", "]", m)
+ m = re.sub(r"\\left[ ]*\([ ]*", "(", m)
+ m = re.sub(r"[ ]*\\right[ ]*\)", ")", m)
+ m = re.sub(r"([^\\])\$", "\\1", m)
+
+ m = m.replace("\\times", "x")
+ m = m.replace("\\pm", "+-")
+ m = m.replace("\\cdot", "*")
+ m = m.replace("\\sim", "~")
+ m = m.replace("\\leftarrow", "<-")
+ m = m.replace("\\rightarrow", "->")
+ m = m.replace("\\leftrightarrow", "<->")
+ m = re.sub(r" *\\neg *", " !", m)
+ m = re.sub(r" *\\neq? *", " != ", m)
+ m = re.sub(r" *\\geq? *", " >= ", m)
+ m = re.sub(r" *\\leq? *", " <= ", m)
+ m = re.sub(r" *\\vee *", " V ", m)
+ m = re.sub(r" *\\oplus *", " (+) ", m)
+ m = re.sub(r" *\\mod *", " mod ", m)
+ m = re.sub(r"( *)\\partial *", "\\1d", m)
+
+ m = re.sub(r"( *)\\quad *", "\\1 ", m)
+ m = m.replace("\\,", " ")
+ m = m.replace("\\:", " ")
+ m = m.replace("\\;", " ")
+ m = m.replace("\\!", "")
+
+ m = m.replace("\\\\", "<BR>")
+ m = m.replace("\\wedge", "/\\\\")
+ m = re.sub(r"\\(.)", "\\1", m)
+
+ m = re.sub(r"\([ ]+", "(", m)
+ m = re.sub(r"[ ]+(\.|,|\))(<BR>| |$)", "\\1\\2", m)
+ m = re.sub(r" +\|[ ]+([a-zA-Z0-9_(])", " |\\1", m)
+ m = re.sub(r"([a-zA-Z0-9_)}])[ ]+(\(|\|)", "\\1\\2", m)
+
+ m = re.sub(r"{\((-?[a-zA-Z0-9_]+)\)}", "\\1", m)
+ m = re.sub(r"{(-?[a-zA-Z0-9_]+)}", "(\\1)", m)
+ m = re.sub(r"\(([0-9]+)\)", "\\1", m)
+ m = m.replace("{", "(")
+ m = m.replace("}", ")")
+
+ #print "%s ===> %s" % (match.group(0), m)
+ return m
if __name__ == "__main__":
if len(sys.argv) < 2:
print "Usage:\n", os.path.basename(sys.argv[0]), " <module path>"
exit(0)
+
+ if len(sys.argv) >= 3:
+ if sys.argv[2].lower() == "verbose":
+ verbose = True
rst_parser_dir = os.path.dirname(os.path.abspath(sys.argv[0]))
hdr_parser_path = os.path.join(rst_parser_dir, "../python/src2")
parser.parse(module, os.path.join(rst_parser_dir, "../" + module))
# summary
- print
- print "RST Parser Summary:"
- print " Total sections: %s" % parser.sections_total
- print " Skipped sections: %s" % parser.sections_skipped
- print " Parsed sections: %s" % parser.sections_parsed
- print " Invalid sections: %s" % (parser.sections_total - parser.sections_parsed - parser.sections_skipped)
-
- # statistic by language
- stat = {}
- classes = 0
- structs = 0
- for name, d in parser.definitions.items():
- if d.get("isclass", False):
- classes += 1
- elif d.get("isstruct", False):
- structs += 1
- else:
- for decl in d.get("decls",[]):
- stat[decl[0]] = stat.get(decl[0],0) + 1
-
- print
- print " classes documented: %s" % classes
- print " structs documented: %s" % structs
- for lang in sorted(stat.items()):
- print " %7s functions documented: %s" % lang
-
-# sys.exit(0)
- # for name, d in parser.definitions.items():
- # print
- # print ToJavadoc(d, d.get("params",{}).keys())
-
+ parser.printSummary()