ben
/
mwparserfromhell
mirror of https://github.com/earwig/mwparserfromhell
1
1
Fork 0
Code Releases 24 Activity
Browse Source

Merge branch 'feature/speedup' into develop

tags/v0.2
Ben Kurtovic 11 years ago
parent
6413ae21da ca11d77efd
commit
eba76dc05c
7 changed files with 1774 additions and 22 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. +3
    -2
      docs/conf.py
  2. +24
    -0
      mwparserfromhell/parser/builder.c
  3. +1454
    -0
      mwparserfromhell/parser/tokenizer.c
  4. +269
    -0
      mwparserfromhell/parser/tokenizer.h
  5. +8
    -11
      mwparserfromhell/parser/tokenizer.py
  6. +8
    -8
      mwparserfromhell/wikicode.py
  7. +8
    -1
      setup.py

+ 3
- 2
docs/conf.py View File

@@ -17,6 +17,7 @@ import sys, os
# add these directories to sys.path here. If the directory is relative to the
# documentation root, use os.path.abspath to make it absolute, like shown here.
sys.path.insert(0, os.path.abspath('..'))
import mwparserfromhell

# -- General configuration -----------------------------------------------------

@@ -48,9 +49,9 @@ copyright = u'2012 Ben Kurtovic'
# built documents.
#
# The short X.Y version.
version = '0.2'
version = ".".join(mwparserfromhell.__version__.split(".", 2)[:2])
# The full version, including alpha/beta/rc tags.
release = '0.2.dev'
release = mwparserfromhell.__version__

# The language for content autogenerated by Sphinx. Refer to documentation
# for a list of supported languages.


+ 24
- 0
mwparserfromhell/parser/builder.c View File

@@ -0,0 +1,24 @@
/*
Builder for MWParserFromHell
Copyright (C) 2012 Ben Kurtovic <ben.kurtovic@verizon.net>

Permission is hereby granted, free of charge, to any person obtaining a copy of
this software and associated documentation files (the "Software"), to deal in
the Software without restriction, including without limitation the rights to
use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
of the Software, and to permit persons to whom the Software is furnished to do
so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
*/

#include <Python.h>

+ 1454
- 0
mwparserfromhell/parser/tokenizer.c
File diff suppressed because it is too large
View File


+ 269
- 0
mwparserfromhell/parser/tokenizer.h View File

@@ -0,0 +1,269 @@
/*
Tokenizer Header File for MWParserFromHell
Copyright (C) 2012 Ben Kurtovic <ben.kurtovic@verizon.net>

Permission is hereby granted, free of charge, to any person obtaining a copy of
this software and associated documentation files (the "Software"), to deal in
the Software without restriction, including without limitation the rights to
use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
of the Software, and to permit persons to whom the Software is furnished to do
so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
*/

#ifndef PY_SSIZE_T_CLEAN
#define PY_SSIZE_T_CLEAN
#endif

#include <Python.h>
#include <math.h>
#include <structmember.h>

#define malloc PyObject_Malloc
#define free PyObject_Free

static const char* MARKERS[] = {
"{", "}", "[", "]", "<", ">", "|", "=", "&", "#", "*", ";", ":", "/", "-",
"!", "\n", ""};

#define NUM_MARKERS 18
#define TEXTBUFFER_BLOCKSIZE 1024
#define MAX_ENTITY_SIZE 8

static int route_state = 0;
#define BAD_ROUTE (route_state)
#define FAIL_ROUTE() (route_state = 1)
#define RESET_ROUTE() (route_state = 0)

static char** entitydefs;

static PyObject* EMPTY;
static PyObject* NOARGS;
static PyObject* tokens;


/* Tokens */

static PyObject* Text;

static PyObject* TemplateOpen;
static PyObject* TemplateParamSeparator;
static PyObject* TemplateParamEquals;
static PyObject* TemplateClose;

static PyObject* ArgumentOpen;
static PyObject* ArgumentSeparator;
static PyObject* ArgumentClose;

static PyObject* WikilinkOpen;
static PyObject* WikilinkSeparator;
static PyObject* WikilinkClose;

static PyObject* HTMLEntityStart;
static PyObject* HTMLEntityNumeric;
static PyObject* HTMLEntityHex;
static PyObject* HTMLEntityEnd;
static PyObject* HeadingStart;
static PyObject* HeadingEnd;

static PyObject* CommentStart;
static PyObject* CommentEnd;

static PyObject* TagOpenOpen;
static PyObject* TagAttrStart;
static PyObject* TagAttrEquals;
static PyObject* TagAttrQuote;
static PyObject* TagCloseOpen;
static PyObject* TagCloseSelfclose;
static PyObject* TagOpenClose;
static PyObject* TagCloseClose;


/* Local contexts: */

#define LC_TEMPLATE 0x00007
#define LC_TEMPLATE_NAME 0x00001
#define LC_TEMPLATE_PARAM_KEY 0x00002
#define LC_TEMPLATE_PARAM_VALUE 0x00004

#define LC_ARGUMENT 0x00018
#define LC_ARGUMENT_NAME 0x00008
#define LC_ARGUMENT_DEFAULT 0x00010

#define LC_WIKILINK 0x00060
#define LC_WIKILINK_TITLE 0x00020
#define LC_WIKILINK_TEXT 0x00040

#define LC_HEADING 0x01F80
#define LC_HEADING_LEVEL_1 0x00080
#define LC_HEADING_LEVEL_2 0x00100
#define LC_HEADING_LEVEL_3 0x00200
#define LC_HEADING_LEVEL_4 0x00400
#define LC_HEADING_LEVEL_5 0x00800
#define LC_HEADING_LEVEL_6 0x01000

#define LC_COMMENT 0x02000

#define LC_HAS_TEXT 0x04000
#define LC_FAIL_ON_TEXT 0x08000
#define LC_FAIL_NEXT 0x10000
#define LC_FAIL_ON_LBRACE 0x20000
#define LC_FAIL_ON_RBRACE 0x40000
#define LC_FAIL_ON_EQUALS 0x80000

/* Global contexts: */

#define GL_HEADING 0x1


/* Miscellaneous structs: */

struct Textbuffer {
Py_ssize_t size;
Py_UNICODE* data;
struct Textbuffer* next;
};

struct Stack {
PyObject* stack;
int context;
struct Textbuffer* textbuffer;
struct Stack* next;
};

typedef struct {
PyObject* title;
int level;
} HeadingData;


/* Tokenizer object definition: */

typedef struct {
PyObject_HEAD
PyObject* text; /* text to tokenize */
struct Stack* topstack; /* topmost stack */
Py_ssize_t head; /* current position in text */
Py_ssize_t length; /* length of text */
int global; /* global context */
} Tokenizer;


/* Macros for accessing Tokenizer data: */

#define Tokenizer_READ(self, delta) (*PyUnicode_AS_UNICODE(Tokenizer_read(self, delta)))


/* Function prototypes: */

static PyObject* Tokenizer_new(PyTypeObject*, PyObject*, PyObject*);
static struct Textbuffer* Textbuffer_new(void);
static void Tokenizer_dealloc(Tokenizer*);
static void Textbuffer_dealloc(struct Textbuffer*);
static int Tokenizer_init(Tokenizer*, PyObject*, PyObject*);
static int Tokenizer_push(Tokenizer*, int);
static PyObject* Textbuffer_render(struct Textbuffer*);
static int Tokenizer_push_textbuffer(Tokenizer*);
static void Tokenizer_delete_top_of_stack(Tokenizer*);
static PyObject* Tokenizer_pop(Tokenizer*);
static PyObject* Tokenizer_pop_keeping_context(Tokenizer*);
static void* Tokenizer_fail_route(Tokenizer*);
static int Tokenizer_write(Tokenizer*, PyObject*);
static int Tokenizer_write_first(Tokenizer*, PyObject*);
static int Tokenizer_write_text(Tokenizer*, Py_UNICODE);
static int Tokenizer_write_all(Tokenizer*, PyObject*);
static int Tokenizer_write_text_then_stack(Tokenizer*, const char*);
static PyObject* Tokenizer_read(Tokenizer*, Py_ssize_t);
static PyObject* Tokenizer_read_backwards(Tokenizer*, Py_ssize_t);
static int Tokenizer_parse_template_or_argument(Tokenizer*);
static int Tokenizer_parse_template(Tokenizer*);
static int Tokenizer_parse_argument(Tokenizer*);
static int Tokenizer_handle_template_param(Tokenizer*);
static int Tokenizer_handle_template_param_value(Tokenizer*);
static PyObject* Tokenizer_handle_template_end(Tokenizer*);
static int Tokenizer_handle_argument_separator(Tokenizer*);
static PyObject* Tokenizer_handle_argument_end(Tokenizer*);
static int Tokenizer_parse_wikilink(Tokenizer*);
static int Tokenizer_handle_wikilink_separator(Tokenizer*);
static PyObject* Tokenizer_handle_wikilink_end(Tokenizer*);
static int Tokenizer_parse_heading(Tokenizer*);
static HeadingData* Tokenizer_handle_heading_end(Tokenizer*);
static int Tokenizer_really_parse_entity(Tokenizer*);
static int Tokenizer_parse_entity(Tokenizer*);
static int Tokenizer_parse_comment(Tokenizer*);
static void Tokenizer_verify_safe(Tokenizer*, int, Py_UNICODE);
static PyObject* Tokenizer_parse(Tokenizer*, int);
static PyObject* Tokenizer_tokenize(Tokenizer*, PyObject*);


/* More structs for creating the Tokenizer type: */

static PyMethodDef
Tokenizer_methods[] = {
{"tokenize", (PyCFunction) Tokenizer_tokenize, METH_VARARGS,
"Build a list of tokens from a string of wikicode and return it."},
{NULL}
};

static PyMemberDef
Tokenizer_members[] = {
{NULL}
};

static PyMethodDef
module_methods[] = {
{NULL}
};

static PyTypeObject
TokenizerType = {
PyObject_HEAD_INIT(NULL)
0, /* ob_size */
"_tokenizer.CTokenizer", /* tp_name */
sizeof(Tokenizer), /* tp_basicsize */
0, /* tp_itemsize */
(destructor) Tokenizer_dealloc, /* tp_dealloc */
0, /* tp_print */
0, /* tp_getattr */
0, /* tp_setattr */
0, /* tp_compare */
0, /* tp_repr */
0, /* tp_as_number */
0, /* tp_as_sequence */
0, /* tp_as_mapping */
0, /* tp_hash */
0, /* tp_call */
0, /* tp_str */
0, /* tp_getattro */
0, /* tp_setattro */
0, /* tp_as_buffer */
Py_TPFLAGS_DEFAULT, /* tp_flags */
"Creates a list of tokens from a string of wikicode.", /* tp_doc */
0, /* tp_traverse */
0, /* tp_clear */
0, /* tp_richcompare */
0, /* tp_weaklistoffset */
0, /* tp_iter */
0, /* tp_iternext */
Tokenizer_methods, /* tp_methods */
Tokenizer_members, /* tp_members */
0, /* tp_getset */
0, /* tp_base */
0, /* tp_dict */
0, /* tp_descr_get */
0, /* tp_descr_set */
0, /* tp_dictoffset */
(initproc) Tokenizer_init, /* tp_init */
0, /* tp_alloc */
Tokenizer_new, /* tp_new */
};

+ 8
- 11
mwparserfromhell/parser/tokenizer.py View File

@@ -162,8 +162,8 @@ class Tokenizer(object):
self._head += 2
braces = 2
while self._read() == "{":
braces += 1
self._head += 1
braces += 1
self._push()

while braces:
@@ -197,10 +197,9 @@ class Tokenizer(object):
except BadRoute:
self._head = reset
raise
else:
self._write_first(tokens.TemplateOpen())
self._write_all(template)
self._write(tokens.TemplateClose())
self._write_first(tokens.TemplateOpen())
self._write_all(template)
self._write(tokens.TemplateClose())

def _parse_argument(self):
"""Parse an argument at the head of the wikicode string."""
@@ -210,10 +209,9 @@ class Tokenizer(object):
except BadRoute:
self._head = reset
raise
else:
self._write_first(tokens.ArgumentOpen())
self._write_all(argument)
self._write(tokens.ArgumentClose())
self._write_first(tokens.ArgumentOpen())
self._write_all(argument)
self._write(tokens.ArgumentClose())

def _verify_safe(self, unsafes):
"""Verify that there are no unsafe characters in the current stack.
@@ -249,8 +247,7 @@ class Tokenizer(object):
except BadRoute:
self._pop()
raise
else:
self._write_all(self._pop(keep_context=True))
self._write_all(self._pop(keep_context=True))
self._context ^= contexts.TEMPLATE_PARAM_KEY
self._context |= contexts.TEMPLATE_PARAM_VALUE
self._write(tokens.TemplateParamEquals())


+ 8
- 8
mwparserfromhell/wikicode.py View File

@@ -386,12 +386,12 @@ class Wikicode(StringMixIn):
With *flat* as ``True``, each returned section contains all of its
subsections within the :py:class:`~.Wikicode`; otherwise, the returned
sections contain only the section up to the next heading, regardless of
its size. If *matches* is given, it should be a regex to matched
its size. If *matches* is given, it should be a regex to be matched
against the titles of section headings; only sections whose headings
match the regex will be included. If *levels* is given, it should be a =
list of integers; only sections whose heading levels are within the
list will be returned. If *include_headings* is ``True``, the section's
literal :py:class:`~.Heading` object will be included in returned
match the regex will be included. If *levels* is given, it should be a
iterable of integers; only sections whose heading levels are within it
will be returned. If *include_headings* is ``True``, the section's
beginning :py:class:`~.Heading` object will be included in returned
:py:class:`~.Wikicode` objects; otherwise, this is skipped.
"""
if matches:
@@ -402,16 +402,16 @@ class Wikicode(StringMixIn):
headings = [head for head in headings if head.level in levels]

sections = []
buffers = [[maxsize, 0]]
buffers = [(maxsize, 0)]
i = 0
while i < len(self.nodes):
if self.nodes[i] in headings:
this = self.nodes[i].level
for (level, start) in buffers:
if not flat or this <= level:
buffers.remove([level, start])
buffers.remove((level, start))
sections.append(Wikicode(self.nodes[start:i]))
buffers.append([this, i])
buffers.append((this, i))
if not include_headings:
i += 1
i += 1


+ 8
- 1
setup.py View File

@@ -21,16 +21,23 @@
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.

from setuptools import setup, find_packages
from setuptools import setup, find_packages, Extension

from mwparserfromhell import __version__

with open("README.rst") as fp:
long_docs = fp.read()

builder = Extension("mwparserfromhell.parser._builder",
sources = ["mwparserfromhell/parser/builder.c"])

tokenizer = Extension("mwparserfromhell.parser._tokenizer",
sources = ["mwparserfromhell/parser/tokenizer.c"])

setup(
name = "mwparserfromhell",
packages = find_packages(exclude=("tests",)),
ext_modules = [builder, tokenizer],
test_suite = "tests",
version = __version__,
author = "Ben Kurtovic",


Write Preview
Loading…
Cancel
Save