Improved RST parser; fixed small typos found by new parser

This commit is contained in:
Andrey Kamaev 2011-07-07 11:23:51 +00:00
parent edf0b40d42
commit 741a689f65
14 changed files with 169 additions and 61 deletions

View File

@ -176,6 +176,8 @@ The structure ``CvGraphScanner`` is used for depth-first graph traversal. See di
CvTreeNodeIterator CvTreeNodeIterator
------------------ ------------------
.. ocv:struct:: CvTreeNodeIterator
The structure ``CvTreeNodeIterator`` is used to traverse trees of sequences. The structure ``CvTreeNodeIterator`` is used to traverse trees of sequences.
ClearGraph ClearGraph

View File

@ -2398,7 +2398,7 @@ For some values of ``p`` , such as integer values, 0.5 and -0.5, specialized fas
RNG RNG
--- ---
.. ocv:class: RNG .. ocv:class:: RNG
Random number generator. It encapsulates the state (currently, a 64-bit integer) and has methods to return scalar random values and to fill arrays with random values. Currently it supports uniform and Gaussian (normal) distributions. The generator uses Multiply-With-Carry algorithm, introduced by G. Marsaglia ( Random number generator. It encapsulates the state (currently, a 64-bit integer) and has methods to return scalar random values and to fill arrays with random values. Currently it supports uniform and Gaussian (normal) distributions. The generator uses Multiply-With-Carry algorithm, introduced by G. Marsaglia (
http://en.wikipedia.org/wiki/Multiply-with-carry http://en.wikipedia.org/wiki/Multiply-with-carry

View File

@ -7,7 +7,7 @@ Matrix Reductions
gpu::meanStdDev gpu::meanStdDev
------------------- -------------------
.. cpp:function:: void gpu::meanStdDev(const GpuMat\& mtx, Scalar\& mean, Scalar\& stddev) .. ocv:function:: void gpu::meanStdDev(const GpuMat\& mtx, Scalar\& mean, Scalar\& stddev)
Computes a mean value and a standard deviation of matrix elements. Computes a mean value and a standard deviation of matrix elements.

View File

@ -48,7 +48,7 @@ class ParamParser(object):
offset = line.find(":param") offset = line.find(":param")
assert offset > 0 assert offset > 0
self.prefix = line[:offset] self.prefix = line[:offset]
assert self.prefix==" "*len(self.prefix) assert self.prefix==" "*len(self.prefix), ":param definition should be prefixed with spaces"
line = line[offset + 6:].lstrip() line = line[offset + 6:].lstrip()
name_end = line.find(":") name_end = line.find(":")
assert name_end > 0 assert name_end > 0
@ -72,25 +72,46 @@ class RstParser(object):
def __init__(self, cpp_parser): def __init__(self, cpp_parser):
self.cpp_parser = cpp_parser self.cpp_parser = cpp_parser
self.definitions = {} self.definitions = {}
self.sections_parsed = 0
self.sections_total = 0
self.sections_skipped = 0
def parse(self, module_path): def parse(self, module_name, module_path=None):
if module_path is None:
module_path = "../" + module_name
doclist = glob.glob(os.path.join(module_path,"doc/*.rst")) doclist = glob.glob(os.path.join(module_path,"doc/*.rst"))
for doc in doclist: for doc in doclist:
self.parse_rst_file(doc) self.parse_rst_file(module_name, doc)
def parse_section_safe(self, module_name, section_name, file_name, lineno, lines):
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
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)
self.sections_skipped += 1
return
def parse_section(self, section_name, file_name, lineno, lines):
func = {} func = {}
func["name"] = section_name func["name"] = section_name
func["file"] = file_name func["file"] = file_name
func["line"] = lineno func["line"] = lineno
func["module"] = module_name
# parse section name # parse section name
class_separator_idx = func["name"].find("::") section_name = self.parse_namespace(func, section_name)
class_separator_idx = section_name.find("::")
if class_separator_idx > 0: if class_separator_idx > 0:
func["class"] = func["name"][:class_separator_idx] func["class"] = section_name[:class_separator_idx]
func["method"] = func["name"][class_separator_idx+2:] func["method"] = section_name[class_separator_idx+2:]
else: else:
func["method"] = func["name"] func["method"] = section_name
skip_code_lines = False skip_code_lines = False
expected_brief = True expected_brief = True
@ -107,7 +128,7 @@ class RstParser(object):
# skip lines if line-skipping mode is activated # skip lines if line-skipping mode is activated
if skip_code_lines: if skip_code_lines:
if not l or l.startswith(" ") or l.startswith("\t"): if not l or l.startswith(" "):
continue continue
else: else:
skip_code_lines = False skip_code_lines = False
@ -186,6 +207,9 @@ class RstParser(object):
func["long"] = func.get("long", "") + "\n" + ll func["long"] = func.get("long", "") + "\n" + ll
# endfor l in lines # 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)
# save last parameter if needed # save last parameter if needed
if pdecl.active: if pdecl.active:
self.add_new_pdecl(func, pdecl) self.add_new_pdecl(func, pdecl)
@ -194,13 +218,17 @@ class RstParser(object):
func = self.normalize(func) func = self.normalize(func)
if self.validate(func): if self.validate(func):
self.definitions[func["name"]] = func self.definitions[func["name"]] = func
self.sections_parsed += 1
#self.print_info(func) #self.print_info(func)
elif func: elif func:
self.print_info(func, True) self.print_info(func, True)
pass
def parse_rst_file(self, doc): def parse_rst_file(self, module_name, doc):
doc = os.path.abspath(doc) doc = os.path.abspath(doc)
lineno = 0 lineno = 0
whitespace_warnings = 0
max_whitespace_warnings = 10
lines = [] lines = []
flineno = 0 flineno = 0
@ -210,14 +238,23 @@ class RstParser(object):
df = open(doc, "rt") df = open(doc, "rt")
for l in df.readlines(): for l in df.readlines():
lineno += 1 lineno += 1
# 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)
l = l.replace("\t", " ")
# handle first line
if prev_line == None: if prev_line == None:
prev_line = l.rstrip() prev_line = l.rstrip()
continue continue
ll = l.rstrip() ll = l.rstrip()
if len(prev_line) > 0 and len(ll) >= len(prev_line) and ll == "-" * len(ll): if len(prev_line) > 0 and len(ll) >= len(prev_line) and ll == "-" * len(ll):
# new function candidate # new function candidate
if len(lines) > 1: if len(lines) > 1:
self.parse_section(fname, doc, flineno, lines[:len(lines)-1]) self.parse_section_safe(module_name, fname, doc, flineno, lines[:len(lines)-1])
lines = [] lines = []
flineno = lineno-1 flineno = lineno-1
fname = prev_line.strip() fname = prev_line.strip()
@ -228,7 +265,16 @@ class RstParser(object):
# don't forget about the last function section in file!!! # don't forget about the last function section in file!!!
if len(lines) > 1: if len(lines) > 1:
self.parse_section(fname, doc, flineno, lines[:len(lines)]) self.parse_section_safe(module_name, fname, doc, flineno, lines[:len(lines)])
def parse_namespace(self, func, section_name):
known_namespaces = ["cv", "gpu", "flann"]
l = section_name.strip()
for namespace in known_namespaces:
if l.startswith(namespace + "::"):
func["namespace"] = namespace
return l[len(namespace)+2:]
return section_name
def add_new_fdecl(self, func, decl): def add_new_fdecl(self, func, decl):
decls = func.get("decls",[]) decls = func.get("decls",[])
@ -242,40 +288,43 @@ class RstParser(object):
def add_new_pdecl(self, func, decl): def add_new_pdecl(self, func, decl):
params = func.get("params",{}) params = func.get("params",{})
if decl.name in params: if decl.name in params:
print "Parser error: parameter \"%s\" for %s is defined multiple times. See %s line %s" \ print "RST parser error: redefinition of parameter \"%s\" in \"%s\" File: %s (line %s)" \
% (decl.name, func["name"], func["file"], func["line"]) % (decl.name, func["name"], func["file"], func["line"])
else: else:
params[decl.name] = decl.comment params[decl.name] = decl.comment
func["params"] = params func["params"] = params
def print_info(self, func, skipped=False): def print_info(self, func, skipped=False):
print "" print
if skipped: if skipped:
print "SKIPPED DEFINITION:" print "SKIPPED DEFINITION:"
print "name: %s" % (func.get("name","~empty~")) print "name: %s" % (func.get("name","~empty~"))
print "file: %s (line %s)" % (func.get("file","~empty~"), func.get("line","~empty~")) print "file: %s (line %s)" % (func.get("file","~empty~"), func.get("line","~empty~"))
print "is class: %s" % func.get("isclass",False) print "is class: %s" % func.get("isclass",False)
print "is struct: %s" % func.get("isstruct",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 "class: %s" % (func.get("class","~empty~"))
print "method: %s" % (func.get("method","~empty~")) print "method: %s" % (func.get("method","~empty~"))
print "brief: %s" % (func.get("brief","~empty~")) print "brief: %s" % (func.get("brief","~empty~"))
if "decls" in func: if "decls" in func:
print "declarations:" print "declarations:"
for d in func["decls"]: for d in func["decls"]:
print " %7s: %s" % (d[0], re.sub(r"[ \t]+", " ", d[1])) print " %7s: %s" % (d[0], re.sub(r"[ ]+", " ", d[1]))
if "params" in func: if "params" in func:
print "parameters:" print "parameters:"
for name, comment in func["params"].items(): for name, comment in func["params"].items():
print "%23s: %s" % (name, comment) print "%23s: %s" % (name, comment)
if not skipped: if not skipped:
print "long: %s" % (func.get("long","~empty~")) print "long: %s" % (func.get("long","~empty~"))
print
def validate(self, func): def validate(self, func):
if func.get("decls",None) is None: if func.get("decls",None) is None:
if not func.get("isclass",False): if not func.get("isclass",False) and not func.get("isstruct",False):
return False return False
if func["name"] in self.definitions: if func["name"] in self.definitions:
print "Parser error: function/class/struct \"%s\" in %s line %s is already documented in %s line %s" \ 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"]) % (func["name"], func["file"], func["line"], self.definitions[func["name"]]["file"], self.definitions[func["name"]]["line"])
return False return False
#todo: validate parameter names #todo: validate parameter names
@ -306,8 +355,32 @@ class RstParser(object):
if cmt: if cmt:
params[name] = cmt params[name] = cmt
func["params"] = params func["params"] = params
# special case for old C functions - section name should omit "cv" prefix
if not func.get("isclass",False) and not func.get("isstruct",False):
self.fixOldCFunctionName(func)
return func return func
def fixOldCFunctionName(self, func):
if not "decls" in func:
return
fname = None
for decl in func["decls"]:
if decl[0] != "C" and decl[0] != "Python1":
return
if decl[0] == "C":
fname = decl[2][0]
if fname is None:
return
fname = fname.replace(".", "::")
if fname == "cv::cv" + func.get("name", ""):
func["name"] = fname[2:]
func["method"] = fname[2:]
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"])
# self.print_info(func)
def normalizeText(self, s): def normalizeText(self, s):
if s is None: if s is None:
return s return s
@ -316,7 +389,7 @@ class RstParser(object):
# remove tailing :: # remove tailing ::
s = re.sub(r"::$", "\n", s) s = re.sub(r"::$", "\n", s)
# remove extra line breaks before/after _ or , # remove extra line breaks before/after _ or ,
s = re.sub(r"\n[ \t]*([_,])\n", r"\1", s) s = re.sub(r"\n[ ]*([_,])\n", r"\1", s)
# remove extra line breaks after ` # remove extra line breaks after `
#s = re.sub(r"`\n", "` ", s) #s = re.sub(r"`\n", "` ", s)
# remove extra line breaks before * # remove extra line breaks before *
@ -326,17 +399,17 @@ class RstParser(object):
# remove extra line breaks after #. # remove extra line breaks after #.
s = re.sub(r"\n#\.\n", "\n#. ", s) s = re.sub(r"\n#\.\n", "\n#. ", s)
# remove extra line breaks before ` # remove extra line breaks before `
s = re.sub(r"\n[ \t]*`", " `", s) s = re.sub(r"\n[ ]*`", " `", s)
# remove trailing whitespaces # remove trailing whitespaces
s = re.sub(r"[ \t]+$", "", s) s = re.sub(r"[ ]+$", "", s)
# remove whitespace before . # remove whitespace before .
s = re.sub(r"[ \t]+\.", "\.", s) s = re.sub(r"[ ]+\.", "\.", s)
# remove .. for references # remove .. for references
s = re.sub(r"\.\. \[", "[", s) s = re.sub(r"\.\. \[", "[", s)
# unescape # unescape
s = re.sub(r"\\(.)", "\\1", s) s = re.sub(r"\\(.)", "\\1", s)
# compress whitespace # compress whitespace
s = re.sub(r"[ \t]+", " ", s) s = re.sub(r"[ ]+", " ", s)
s = s.replace("**", "") s = s.replace("**", "")
s = s.replace("``", "\"") s = s.replace("``", "\"")
@ -363,10 +436,43 @@ if __name__ == "__main__":
module = sys.argv[1] module = sys.argv[1]
if not os.path.isdir(os.path.join(rst_parser_dir, "../" + module)): if module != "all" and not os.path.isdir(os.path.join(rst_parser_dir, "../" + module)):
print "Module \"" + module + "\" could not be found." print "Module \"" + module + "\" could not be found."
exit(1) exit(1)
parser = RstParser(hdr_parser.CppHeaderParser()) parser = RstParser(hdr_parser.CppHeaderParser())
parser.parse(os.path.join(rst_parser_dir, "../" + module))
if module == "all":
for m in ["androidcamera", "calib3d", "contrib", "core", "features2d", "flann", "gpu", "haartraining", "highgui", "imgproc", "java", "legacy", "ml", "objdetect", "ocl", "python", "stitching", "traincascade", "ts", "video"]:
parser.parse(m, os.path.join(rst_parser_dir, "../" + m))
else:
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

View File

@ -480,7 +480,7 @@ Updates the predicted state from the measurement.
BackgroundSubtractor BackgroundSubtractor
-------------------- --------------------
.. ocv:class: BackgroundSubtractor .. ocv:class:: BackgroundSubtractor
Base class for background/foreground segmentation. :: Base class for background/foreground segmentation. ::
@ -522,7 +522,7 @@ Computes a background image.
BackgroundSubtractorMOG BackgroundSubtractorMOG
----------------------- -----------------------
.. ocv:class: BackgroundSubtractorMOG : public BackgroundSubtractor .. ocv:class:: BackgroundSubtractorMOG : public BackgroundSubtractor
Gaussian Mixture-based Backbround/Foreground Segmentation Algorithm. Gaussian Mixture-based Backbround/Foreground Segmentation Algorithm.
@ -567,7 +567,7 @@ BackgroundSubtractorMOG2
------------------------ ------------------------
Gaussian Mixture-based Backbround/Foreground Segmentation Algorithm. Gaussian Mixture-based Backbround/Foreground Segmentation Algorithm.
.. ocv:class: BackgroundSubtractorMOG2 : public BackgroundSubtractor .. ocv:class:: BackgroundSubtractorMOG2 : public BackgroundSubtractor
Here are important members of the class that control the algorithm, which you can set after constructing the class instance: Here are important members of the class that control the algorithm, which you can set after constructing the class instance: