Regex library Nrex initial port
This commit is contained in:
parent
f697ec2fe0
commit
ef005d4f64
17 changed files with 1254 additions and 1206 deletions
64
drivers/nrex/README.md
Normal file
64
drivers/nrex/README.md
Normal file
|
|
@ -0,0 +1,64 @@
|
|||
# NREX: Node RegEx
|
||||
|
||||
Small node-based regular expression library. It only does text pattern
|
||||
matchhing, not replacement. To use add the files `nrex.hpp`, `nrex.cpp`
|
||||
and `nrex_config.h` to your project and follow the example:
|
||||
|
||||
nrex regex;
|
||||
regex.compile("^(fo+)bar$");
|
||||
|
||||
nrex_result captures[regex.capture_size()];
|
||||
if (regex.match("foobar", captures))
|
||||
{
|
||||
std::cout << captures[0].start << std::endl;
|
||||
std::cout << captures[0].length << std::endl;
|
||||
}
|
||||
|
||||
More details about its use is documented in `nrex.hpp`
|
||||
|
||||
Currently supported features:
|
||||
* Capturing `()` and non-capturing `(?:)` groups
|
||||
* Any character `.`
|
||||
* Shorthand caracter classes `\w\W\s\S\d\D`
|
||||
* User-defined character classes such as `[A-Za-z]`
|
||||
* Simple quantifiers `?`, `*` and `+`
|
||||
* Range quantifiers `{0,1}`
|
||||
* Lazy (non-greedy) quantifiers `*?`
|
||||
* Begining `^` and end `$` anchors
|
||||
* Alternation `|`
|
||||
* Backreferences `\1` to `\99`
|
||||
|
||||
To do list:
|
||||
* Unicode `\uFFFF` code points
|
||||
|
||||
## License
|
||||
|
||||
Copyright (c) 2015, Zher Huei Lee
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
1. Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
|
||||
2. Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the distribution.
|
||||
|
||||
3. Neither the name of the copyright holder nor the names of its
|
||||
contributors may be used to endorse or promote products derived from
|
||||
this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS
|
||||
IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
|
||||
TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
|
||||
PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
|
||||
TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
||||
PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
||||
LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
||||
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
||||
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
9
drivers/nrex/SCsub
Normal file
9
drivers/nrex/SCsub
Normal file
|
|
@ -0,0 +1,9 @@
|
|||
|
||||
Import('env')
|
||||
|
||||
sources = [
|
||||
'nrex.cpp',
|
||||
'regex.cpp',
|
||||
]
|
||||
env.add_source_files(env.drivers_sources, sources)
|
||||
|
||||
902
drivers/nrex/nrex.cpp
Normal file
902
drivers/nrex/nrex.cpp
Normal file
|
|
@ -0,0 +1,902 @@
|
|||
// NREX: Node RegEx
|
||||
//
|
||||
// Copyright (c) 2015, Zher Huei Lee
|
||||
// All rights reserved.
|
||||
//
|
||||
// This software is provided 'as-is', without any express or implied
|
||||
// warranty. In no event will the authors be held liable for any damages
|
||||
// arising from the use of this software.
|
||||
//
|
||||
// Permission is granted to anyone to use this software for any purpose,
|
||||
// including commercial applications, and to alter it and redistribute it
|
||||
// freely, subject to the following restrictions:
|
||||
//
|
||||
// 1. The origin of this software must not be misrepresented; you must not
|
||||
// claim that you wrote the original software. If you use this software
|
||||
// in a product, an acknowledgment in the product documentation would
|
||||
// be appreciated but is not required.
|
||||
//
|
||||
// 2. Altered source versions must be plainly marked as such, and must not
|
||||
// be misrepresented as being the original software.
|
||||
//
|
||||
// 3. This notice may not be removed or altered from any source
|
||||
// distribution.
|
||||
//
|
||||
|
||||
#include "nrex.hpp"
|
||||
|
||||
#ifdef NREX_UNICODE
|
||||
#include <wctype.h>
|
||||
#include <wchar.h>
|
||||
#define NREX_ISALPHANUM iswalnum
|
||||
#define NREX_STRLEN wcslen
|
||||
#else
|
||||
#include <ctype.h>
|
||||
#include <string.h>
|
||||
#define NREX_ISALPHANUM isalnum
|
||||
#define NREX_STRLEN strlen
|
||||
#endif
|
||||
|
||||
#ifdef NREX_THROW_ERROR
|
||||
#define NREX_COMPILE_ERROR(M) throw nrex_compile_error(M)
|
||||
#else
|
||||
#define NREX_COMPILE_ERROR(M) reset(); return false
|
||||
#endif
|
||||
|
||||
#ifndef NREX_NEW
|
||||
#define NREX_NEW(X) new X
|
||||
#define NREX_NEW_ARRAY(X, N) new X[N]
|
||||
#define NREX_DELETE(X) delete X
|
||||
#define NREX_DELETE_ARRAY(X) delete[] X
|
||||
#endif
|
||||
|
||||
template<typename T>
|
||||
class nrex_array
|
||||
{
|
||||
private:
|
||||
T* _data;
|
||||
unsigned int _reserved;
|
||||
unsigned int _size;
|
||||
public:
|
||||
nrex_array()
|
||||
: _data(NREX_NEW_ARRAY(T, 2))
|
||||
, _reserved(2)
|
||||
, _size(0)
|
||||
{
|
||||
}
|
||||
|
||||
~nrex_array()
|
||||
{
|
||||
NREX_DELETE_ARRAY(_data);
|
||||
}
|
||||
|
||||
unsigned int size() const
|
||||
{
|
||||
return _size;
|
||||
}
|
||||
|
||||
void reserve(unsigned int size)
|
||||
{
|
||||
T* old = _data;
|
||||
_data = NREX_NEW_ARRAY(T, size);
|
||||
_reserved = size;
|
||||
for (unsigned int i = 0; i < _size; ++i)
|
||||
{
|
||||
_data[i] = old[i];
|
||||
}
|
||||
NREX_DELETE_ARRAY(old);
|
||||
}
|
||||
|
||||
void push(T item)
|
||||
{
|
||||
if (_size == _reserved)
|
||||
{
|
||||
reserve(_reserved * 2);
|
||||
}
|
||||
_data[_size] = item;
|
||||
_size++;
|
||||
}
|
||||
|
||||
T& top()
|
||||
{
|
||||
return _data[_size - 1];
|
||||
}
|
||||
|
||||
const T& operator[] (unsigned int i) const
|
||||
{
|
||||
return _data[i];
|
||||
}
|
||||
|
||||
void pop()
|
||||
{
|
||||
if (_size > 0)
|
||||
{
|
||||
--_size;
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
static nrex_char nrex_unescape(nrex_char repr)
|
||||
{
|
||||
switch (repr)
|
||||
{
|
||||
case '^': return '^';
|
||||
case '$': return '$';
|
||||
case '(': return '(';
|
||||
case ')': return ')';
|
||||
case '\\': return '\\';
|
||||
case '.': return '.';
|
||||
case '+': return '+';
|
||||
case '*': return '*';
|
||||
case '?': return '?';
|
||||
case '-': return '-';
|
||||
case 'a': return '\a';
|
||||
case 'e': return '\e';
|
||||
case 'f': return '\f';
|
||||
case 'n': return '\n';
|
||||
case 'r': return '\r';
|
||||
case 't': return '\t';
|
||||
case 'v': return '\v';
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
struct nrex_search
|
||||
{
|
||||
public:
|
||||
const nrex_char* str;
|
||||
nrex_result* captures;
|
||||
int end;
|
||||
bool complete;
|
||||
|
||||
nrex_char at(int pos)
|
||||
{
|
||||
return str[pos];
|
||||
}
|
||||
|
||||
nrex_search(const nrex_char* str, nrex_result* captures)
|
||||
: str(str)
|
||||
, captures(captures)
|
||||
, end(0)
|
||||
{
|
||||
}
|
||||
};
|
||||
|
||||
struct nrex_node
|
||||
{
|
||||
nrex_node* next;
|
||||
nrex_node* previous;
|
||||
nrex_node* parent;
|
||||
bool quantifiable;
|
||||
|
||||
nrex_node(bool quantify = false)
|
||||
: next(NULL)
|
||||
, previous(NULL)
|
||||
, parent(NULL)
|
||||
, quantifiable(quantify)
|
||||
{
|
||||
}
|
||||
|
||||
virtual ~nrex_node()
|
||||
{
|
||||
if (next)
|
||||
{
|
||||
delete next;
|
||||
}
|
||||
}
|
||||
|
||||
virtual int test(nrex_search* s, int pos) const
|
||||
{
|
||||
return next ? next->test(s, pos) : -1;
|
||||
}
|
||||
|
||||
virtual int test_parent(nrex_search* s, int pos) const
|
||||
{
|
||||
if (next)
|
||||
{
|
||||
pos = next->test(s, pos);
|
||||
}
|
||||
if (parent && pos >= 0)
|
||||
{
|
||||
pos = parent->test_parent(s, pos);
|
||||
}
|
||||
if (pos >= 0)
|
||||
{
|
||||
s->complete = true;
|
||||
}
|
||||
return pos;
|
||||
}
|
||||
};
|
||||
|
||||
struct nrex_node_group : public nrex_node
|
||||
{
|
||||
int capturing;
|
||||
bool negate;
|
||||
nrex_array<nrex_node*> childset;
|
||||
nrex_node* back;
|
||||
|
||||
nrex_node_group(int capturing)
|
||||
: nrex_node(true)
|
||||
, capturing(capturing)
|
||||
, negate(false)
|
||||
, back(NULL)
|
||||
{
|
||||
}
|
||||
|
||||
virtual ~nrex_node_group()
|
||||
{
|
||||
for (unsigned int i = 0; i < childset.size(); ++i)
|
||||
{
|
||||
delete childset[i];
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
int test(nrex_search* s, int pos) const
|
||||
{
|
||||
if (capturing >= 0)
|
||||
{
|
||||
s->captures[capturing].start = pos;
|
||||
}
|
||||
for (unsigned int i = 0; i < childset.size(); ++i)
|
||||
{
|
||||
s->complete = false;
|
||||
int res = childset[i]->test(s, pos);
|
||||
if (s->complete)
|
||||
{
|
||||
return res;
|
||||
}
|
||||
if ((res >= 0) != negate)
|
||||
{
|
||||
if (capturing >= 0)
|
||||
{
|
||||
s->captures[capturing].length = res - pos;
|
||||
}
|
||||
return next ? next->test(s, res) : res;
|
||||
}
|
||||
}
|
||||
return -1;
|
||||
}
|
||||
|
||||
virtual int test_parent(nrex_search* s, int pos) const
|
||||
{
|
||||
if (capturing >= 0)
|
||||
{
|
||||
s->captures[capturing].length = pos - s->captures[capturing].start;
|
||||
}
|
||||
return nrex_node::test_parent(s, pos);
|
||||
}
|
||||
|
||||
void add_childset()
|
||||
{
|
||||
back = NULL;
|
||||
}
|
||||
|
||||
void add_child(nrex_node* node)
|
||||
{
|
||||
node->parent = this;
|
||||
node->previous = back;
|
||||
if (back)
|
||||
{
|
||||
back->next = node;
|
||||
}
|
||||
else
|
||||
{
|
||||
childset.push(node);
|
||||
}
|
||||
back = node;
|
||||
}
|
||||
|
||||
nrex_node* swap_back(nrex_node* node)
|
||||
{
|
||||
if (!back)
|
||||
{
|
||||
add_child(node);
|
||||
return NULL;
|
||||
}
|
||||
nrex_node* old = back;
|
||||
if (!old->previous)
|
||||
{
|
||||
childset.pop();
|
||||
}
|
||||
back = old->previous;
|
||||
add_child(node);
|
||||
return old;
|
||||
}
|
||||
};
|
||||
|
||||
struct nrex_node_char : public nrex_node
|
||||
{
|
||||
nrex_char ch;
|
||||
|
||||
nrex_node_char(nrex_char c)
|
||||
: nrex_node(true)
|
||||
, ch(c)
|
||||
{
|
||||
}
|
||||
|
||||
int test(nrex_search* s, int pos) const
|
||||
{
|
||||
if (s->end == pos || s->at(pos) != ch)
|
||||
{
|
||||
return -1;
|
||||
}
|
||||
return next ? next->test(s, pos + 1) : pos + 1;
|
||||
}
|
||||
};
|
||||
|
||||
struct nrex_node_range : public nrex_node
|
||||
{
|
||||
nrex_char start;
|
||||
nrex_char end;
|
||||
|
||||
nrex_node_range(nrex_char s, nrex_char e)
|
||||
: nrex_node(true)
|
||||
, start(s)
|
||||
, end(e)
|
||||
{
|
||||
}
|
||||
|
||||
int test(nrex_search* s, int pos) const
|
||||
{
|
||||
if (s->end == pos)
|
||||
{
|
||||
return -1;
|
||||
}
|
||||
nrex_char c = s->at(pos);
|
||||
if (c < start || end < c)
|
||||
{
|
||||
return -1;
|
||||
}
|
||||
return next ? next->test(s, pos + 1) : pos + 1;
|
||||
}
|
||||
};
|
||||
|
||||
static bool nrex_is_whitespace(nrex_char repr)
|
||||
{
|
||||
switch (repr)
|
||||
{
|
||||
case ' ':
|
||||
case '\t':
|
||||
case '\r':
|
||||
case '\n':
|
||||
case '\f':
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
static bool nrex_is_shorthand(nrex_char repr)
|
||||
{
|
||||
switch (repr)
|
||||
{
|
||||
case 'W':
|
||||
case 'w':
|
||||
case 'D':
|
||||
case 'd':
|
||||
case 'S':
|
||||
case 's':
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
struct nrex_node_shorthand : public nrex_node
|
||||
{
|
||||
nrex_char repr;
|
||||
|
||||
nrex_node_shorthand(nrex_char c)
|
||||
: nrex_node(true)
|
||||
, repr(c)
|
||||
{
|
||||
}
|
||||
|
||||
int test(nrex_search* s, int pos) const
|
||||
{
|
||||
if (s->end == pos)
|
||||
{
|
||||
return -1;
|
||||
}
|
||||
bool found = false;
|
||||
bool invert = false;
|
||||
nrex_char c = s->at(pos);
|
||||
switch (repr)
|
||||
{
|
||||
case '.':
|
||||
found = true;
|
||||
break;
|
||||
case 'W':
|
||||
invert = true;
|
||||
case 'w':
|
||||
if (c == '_' || NREX_ISALPHANUM(c))
|
||||
{
|
||||
found = true;
|
||||
}
|
||||
break;
|
||||
case 'D':
|
||||
invert = true;
|
||||
case 'd':
|
||||
if ('0' <= c && c <= '9')
|
||||
{
|
||||
found = true;
|
||||
}
|
||||
break;
|
||||
case 'S':
|
||||
invert = true;
|
||||
case 's':
|
||||
if (nrex_is_whitespace(c))
|
||||
{
|
||||
found = true;
|
||||
}
|
||||
break;
|
||||
}
|
||||
if (found == invert)
|
||||
{
|
||||
return -1;
|
||||
}
|
||||
return next ? next->test(s, pos + 1) : pos + 1;
|
||||
}
|
||||
};
|
||||
|
||||
static bool nrex_is_quantifier(nrex_char repr)
|
||||
{
|
||||
switch (repr)
|
||||
{
|
||||
case '?':
|
||||
case '*':
|
||||
case '+':
|
||||
case '{':
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
struct nrex_node_quantifier : public nrex_node
|
||||
{
|
||||
int min;
|
||||
int max;
|
||||
bool greedy;
|
||||
nrex_node* child;
|
||||
|
||||
nrex_node_quantifier()
|
||||
: nrex_node()
|
||||
, min(0)
|
||||
, max(0)
|
||||
, greedy(true)
|
||||
, child(NULL)
|
||||
{
|
||||
}
|
||||
|
||||
virtual ~nrex_node_quantifier()
|
||||
{
|
||||
if (child)
|
||||
{
|
||||
delete child;
|
||||
}
|
||||
}
|
||||
|
||||
int test(nrex_search* s, int pos) const
|
||||
{
|
||||
nrex_array<int> backtrack;
|
||||
backtrack.push(pos);
|
||||
s->complete = false;
|
||||
while (backtrack.top() <= s->end)
|
||||
{
|
||||
if (max >= 1 && backtrack.size() > (unsigned int)max)
|
||||
{
|
||||
break;
|
||||
}
|
||||
if (!greedy && (unsigned int)min < backtrack.size())
|
||||
{
|
||||
int res = backtrack.top();
|
||||
if (next)
|
||||
{
|
||||
res = next->test(s, res);
|
||||
}
|
||||
if (s->complete)
|
||||
{
|
||||
return res;
|
||||
}
|
||||
if (res >= 0 && parent->test_parent(s, res) >= 0)
|
||||
{
|
||||
return res;
|
||||
}
|
||||
}
|
||||
s->complete = false;
|
||||
int res = child->test(s, backtrack.top());
|
||||
if (s->complete)
|
||||
{
|
||||
return res;
|
||||
}
|
||||
if (res < 0 || res == backtrack.top())
|
||||
{
|
||||
break;
|
||||
}
|
||||
backtrack.push(res);
|
||||
}
|
||||
while (greedy && (unsigned int) min < backtrack.size())
|
||||
{
|
||||
s->complete = false;
|
||||
int res = backtrack.top();
|
||||
if (s->complete)
|
||||
{
|
||||
return res;
|
||||
}
|
||||
if (next)
|
||||
{
|
||||
res = next->test(s, res);
|
||||
}
|
||||
if (res >= 0 && parent->test_parent(s, res) >= 0)
|
||||
{
|
||||
return res;
|
||||
}
|
||||
backtrack.pop();
|
||||
}
|
||||
return -1;
|
||||
}
|
||||
};
|
||||
|
||||
struct nrex_node_anchor : public nrex_node
|
||||
{
|
||||
bool end;
|
||||
|
||||
nrex_node_anchor(bool end)
|
||||
: nrex_node()
|
||||
, end(end)
|
||||
{
|
||||
}
|
||||
|
||||
int test(nrex_search* s, int pos) const
|
||||
{
|
||||
if (!end && pos != 0)
|
||||
{
|
||||
return -1;
|
||||
}
|
||||
else if (end && pos != s->end)
|
||||
{
|
||||
return -1;
|
||||
}
|
||||
return next ? next->test(s, pos) : pos;
|
||||
}
|
||||
};
|
||||
|
||||
struct nrex_node_backreference : public nrex_node
|
||||
{
|
||||
int ref;
|
||||
|
||||
nrex_node_backreference(int ref)
|
||||
: nrex_node(true)
|
||||
, ref(ref)
|
||||
{
|
||||
}
|
||||
|
||||
int test(nrex_search* s, int pos) const
|
||||
{
|
||||
nrex_result& r = s->captures[ref];
|
||||
for (int i = 0; i < r.length; ++i)
|
||||
{
|
||||
if (pos + i >= s->end)
|
||||
{
|
||||
return -1;
|
||||
}
|
||||
if (s->at(r.start + i) != s->at(pos + i))
|
||||
{
|
||||
return -1;
|
||||
}
|
||||
}
|
||||
return next ? next->test(s, pos + r.length) : pos + r.length;
|
||||
}
|
||||
};
|
||||
|
||||
nrex::nrex()
|
||||
: _capturing(0)
|
||||
, _root(NULL)
|
||||
{
|
||||
}
|
||||
|
||||
nrex::~nrex()
|
||||
{
|
||||
if (_root)
|
||||
{
|
||||
delete _root;
|
||||
}
|
||||
}
|
||||
|
||||
bool nrex::valid() const
|
||||
{
|
||||
return (_root != NULL);
|
||||
}
|
||||
|
||||
void nrex::reset()
|
||||
{
|
||||
_capturing = 0;
|
||||
if (_root)
|
||||
{
|
||||
delete _root;
|
||||
}
|
||||
_root = NULL;
|
||||
}
|
||||
|
||||
int nrex::capture_size() const
|
||||
{
|
||||
return _capturing + 1;
|
||||
}
|
||||
|
||||
bool nrex::compile(const nrex_char* pattern)
|
||||
{
|
||||
reset();
|
||||
nrex_node_group* root = NREX_NEW(nrex_node_group(_capturing));
|
||||
nrex_array<nrex_node_group*> stack;
|
||||
stack.push(root);
|
||||
_root = root;
|
||||
|
||||
for (const nrex_char* c = pattern; c[0] != '\0'; ++c)
|
||||
{
|
||||
if (c[0] == '(')
|
||||
{
|
||||
if (c[1] == '?')
|
||||
{
|
||||
if (c[2] == ':')
|
||||
{
|
||||
c = &c[2];
|
||||
nrex_node_group* group = NREX_NEW(nrex_node_group(-1));
|
||||
stack.top()->add_child(group);
|
||||
stack.push(group);
|
||||
}
|
||||
else
|
||||
{
|
||||
NREX_COMPILE_ERROR("unrecognised qualifier for parenthesis");
|
||||
}
|
||||
}
|
||||
else if (_capturing < 99)
|
||||
{
|
||||
nrex_node_group* group = NREX_NEW(nrex_node_group(++_capturing));
|
||||
stack.top()->add_child(group);
|
||||
stack.push(group);
|
||||
}
|
||||
else
|
||||
{
|
||||
nrex_node_group* group = NREX_NEW(nrex_node_group(-1));
|
||||
stack.top()->add_child(group);
|
||||
stack.push(group);
|
||||
}
|
||||
}
|
||||
else if (c[0] == ')')
|
||||
{
|
||||
if (stack.size() > 1)
|
||||
{
|
||||
stack.pop();
|
||||
}
|
||||
else
|
||||
{
|
||||
NREX_COMPILE_ERROR("unexpected ')'");
|
||||
}
|
||||
}
|
||||
else if (c[0] == '[')
|
||||
{
|
||||
nrex_node_group* group = NREX_NEW(nrex_node_group(-1));
|
||||
stack.top()->add_child(group);
|
||||
if (c[1] == '^')
|
||||
{
|
||||
group->negate = true;
|
||||
++c;
|
||||
}
|
||||
while (true)
|
||||
{
|
||||
group->add_childset();
|
||||
++c;
|
||||
if (c[0] == '\0')
|
||||
{
|
||||
NREX_COMPILE_ERROR("unclosed character class '[]'");
|
||||
}
|
||||
if (c[0] == ']')
|
||||
{
|
||||
break;
|
||||
}
|
||||
else if (c[0] == '\\')
|
||||
{
|
||||
nrex_char unescaped = nrex_unescape(c[1]);
|
||||
if (unescaped)
|
||||
{
|
||||
group->add_child(NREX_NEW(nrex_node_char(unescaped)));
|
||||
++c;
|
||||
}
|
||||
else if (nrex_is_shorthand(c[1]))
|
||||
{
|
||||
group->add_child(NREX_NEW(nrex_node_shorthand(c[1])));
|
||||
++c;
|
||||
}
|
||||
else
|
||||
{
|
||||
NREX_COMPILE_ERROR("escape token not recognised");
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
if (c[1] == '-' && c[2] != '\0')
|
||||
{
|
||||
bool range = false;
|
||||
if ('A' <= c[0] && c[0] <= 'Z' && 'A' <= c[2] && c[2] <= 'Z')
|
||||
{
|
||||
range = true;
|
||||
}
|
||||
if ('a' <= c[0] && c[0] <= 'z' && 'a' <= c[2] && c[2] <= 'z')
|
||||
{
|
||||
range = true;
|
||||
}
|
||||
if ('0' <= c[0] && c[0] <= '9' && '0' <= c[2] && c[2] <= '9')
|
||||
{
|
||||
range = true;
|
||||
}
|
||||
if (range)
|
||||
{
|
||||
group->add_child(NREX_NEW(nrex_node_range(c[0], c[2])));
|
||||
c = &c[2];
|
||||
continue;
|
||||
}
|
||||
}
|
||||
group->add_child(NREX_NEW(nrex_node_char(c[0])));
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
else if (nrex_is_quantifier(c[0]))
|
||||
{
|
||||
nrex_node_quantifier* quant = NREX_NEW(nrex_node_quantifier);
|
||||
quant->child = stack.top()->swap_back(quant);
|
||||
if (quant->child == NULL || !quant->child->quantifiable)
|
||||
{
|
||||
NREX_COMPILE_ERROR("element not quantifiable");
|
||||
}
|
||||
quant->child->previous = NULL;
|
||||
quant->child->next = NULL;
|
||||
quant->child->parent = quant;
|
||||
if (c[0] == '?')
|
||||
{
|
||||
quant->min = 0;
|
||||
quant->max = 1;
|
||||
}
|
||||
else if (c[0] == '+')
|
||||
{
|
||||
quant->min = 1;
|
||||
quant->max = -1;
|
||||
}
|
||||
else if (c[0] == '*')
|
||||
{
|
||||
quant->min = 0;
|
||||
quant->max = -1;
|
||||
}
|
||||
else if (c[0] == '{')
|
||||
{
|
||||
bool max_set = false;
|
||||
quant->min = 0;
|
||||
quant->max = -1;
|
||||
while (true)
|
||||
{
|
||||
++c;
|
||||
if (c[0] == '\0')
|
||||
{
|
||||
NREX_COMPILE_ERROR("unclosed range quantifier '{}'");
|
||||
}
|
||||
else if (c[0] == '}')
|
||||
{
|
||||
break;
|
||||
}
|
||||
else if (c[0] == ',')
|
||||
{
|
||||
max_set = true;
|
||||
continue;
|
||||
}
|
||||
else if (c[0] < '0' || '9' < c[0])
|
||||
{
|
||||
NREX_COMPILE_ERROR("expected numeric digits, ',' or '}'");
|
||||
}
|
||||
if (max_set)
|
||||
{
|
||||
if (quant->max < 0)
|
||||
{
|
||||
quant->max = int(c[0] - '0');
|
||||
}
|
||||
else
|
||||
{
|
||||
quant->max = quant->max * 10 + int(c[0] - '0');
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
quant->min = quant->min * 10 + int(c[0] - '0');
|
||||
}
|
||||
}
|
||||
if (!max_set)
|
||||
{
|
||||
quant->max = quant->min;
|
||||
}
|
||||
}
|
||||
if (c[1] == '?')
|
||||
{
|
||||
quant->greedy = false;
|
||||
++c;
|
||||
}
|
||||
}
|
||||
else if (c[0] == '|')
|
||||
{
|
||||
stack.top()->add_childset();
|
||||
}
|
||||
else if (c[0] == '^' || c[0] == '$')
|
||||
{
|
||||
stack.top()->add_child(NREX_NEW(nrex_node_anchor((c[0] == '$'))));
|
||||
}
|
||||
else if (c[0] == '.')
|
||||
{
|
||||
stack.top()->add_child(NREX_NEW(nrex_node_shorthand('.')));
|
||||
}
|
||||
else if (c[0] == '\\')
|
||||
{
|
||||
nrex_char unescaped = nrex_unescape(c[1]);
|
||||
if (unescaped)
|
||||
{
|
||||
stack.top()->add_child(NREX_NEW(nrex_node_char(unescaped)));
|
||||
++c;
|
||||
}
|
||||
else if (nrex_is_shorthand(c[1]))
|
||||
{
|
||||
stack.top()->add_child(NREX_NEW(nrex_node_shorthand(c[1])));
|
||||
++c;
|
||||
}
|
||||
else if ('1' <= c[1] && c[1] <= '9')
|
||||
{
|
||||
int ref = 0;
|
||||
if ('0' <= c[2] && c[2] <= '9')
|
||||
{
|
||||
ref = int(c[1] - '0') * 10 + int(c[2] - '0');
|
||||
c = &c[2];
|
||||
}
|
||||
else
|
||||
{
|
||||
ref = int(c[1] - '0');
|
||||
++c;
|
||||
}
|
||||
if (ref > _capturing)
|
||||
{
|
||||
NREX_COMPILE_ERROR("backreference to non-existent capture");
|
||||
}
|
||||
stack.top()->add_child(NREX_NEW(nrex_node_backreference(ref)));
|
||||
}
|
||||
else
|
||||
{
|
||||
NREX_COMPILE_ERROR("escape token not recognised");
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
stack.top()->add_child(NREX_NEW(nrex_node_char(c[0])));
|
||||
}
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
bool nrex::match(const nrex_char* str, nrex_result* captures, int offset, int end) const
|
||||
{
|
||||
nrex_search s(str, captures);
|
||||
if (end >= offset)
|
||||
{
|
||||
s.end = end;
|
||||
}
|
||||
else
|
||||
{
|
||||
s.end = NREX_STRLEN(str);
|
||||
}
|
||||
for (int i = offset; i < s.end; ++i)
|
||||
{
|
||||
for (int c = 0; c <= _capturing; ++c)
|
||||
{
|
||||
captures[c].start = 0;
|
||||
captures[c].length = 0;
|
||||
}
|
||||
if (_root->test(&s, i) >= 0)
|
||||
{
|
||||
return true;
|
||||
}
|
||||
}
|
||||
return false;
|
||||
}
|
||||
144
drivers/nrex/nrex.hpp
Normal file
144
drivers/nrex/nrex.hpp
Normal file
|
|
@ -0,0 +1,144 @@
|
|||
// NREX: Node RegEx
|
||||
//
|
||||
// Copyright (c) 2015, Zher Huei Lee
|
||||
// All rights reserved.
|
||||
//
|
||||
// This software is provided 'as-is', without any express or implied
|
||||
// warranty. In no event will the authors be held liable for any damages
|
||||
// arising from the use of this software.
|
||||
//
|
||||
// Permission is granted to anyone to use this software for any purpose,
|
||||
// including commercial applications, and to alter it and redistribute it
|
||||
// freely, subject to the following restrictions:
|
||||
//
|
||||
// 1. The origin of this software must not be misrepresented; you must not
|
||||
// claim that you wrote the original software. If you use this software
|
||||
// in a product, an acknowledgment in the product documentation would
|
||||
// be appreciated but is not required.
|
||||
//
|
||||
// 2. Altered source versions must be plainly marked as such, and must not
|
||||
// be misrepresented as being the original software.
|
||||
//
|
||||
// 3. This notice may not be removed or altered from any source
|
||||
// distribution.
|
||||
//
|
||||
|
||||
#ifndef NREX_HPP
|
||||
#define NREX_HPP
|
||||
|
||||
#include "nrex_config.h"
|
||||
|
||||
#ifdef NREX_UNICODE
|
||||
typedef wchar_t nrex_char;
|
||||
#else
|
||||
typedef char nrex_char;
|
||||
#endif
|
||||
|
||||
/*!
|
||||
* \brief Struct to contain the range of a capture result
|
||||
*
|
||||
* The range provided is relative to the begining of the searched string.
|
||||
*
|
||||
* \see nrex_node::match()
|
||||
*/
|
||||
struct nrex_result
|
||||
{
|
||||
public:
|
||||
int start; /*!< Start of text range */
|
||||
int length; /*!< Length of text range */
|
||||
};
|
||||
|
||||
class nrex_node;
|
||||
|
||||
/*!
|
||||
* \brief Holds the compiled regex pattern
|
||||
*/
|
||||
class nrex
|
||||
{
|
||||
private:
|
||||
int _capturing;
|
||||
nrex_node* _root;
|
||||
public:
|
||||
nrex();
|
||||
~nrex();
|
||||
|
||||
/*!
|
||||
* \brief Removes the compiled regex and frees up the memory
|
||||
*/
|
||||
void reset();
|
||||
|
||||
/*!
|
||||
* \brief Checks if there is a compiled regex being stored
|
||||
* \return True if present, False if not present
|
||||
*/
|
||||
bool valid() const;
|
||||
|
||||
/*!
|
||||
* \brief Provides number of captures the compiled regex uses
|
||||
*
|
||||
* This is used to provide the array size of the captures needed for
|
||||
* nrex::match() to work. The size is actually the number of capture
|
||||
* groups + one for the matching of the entire pattern. The result is
|
||||
* always capped at 100.
|
||||
*
|
||||
* \return The number of captures
|
||||
*/
|
||||
int capture_size() const;
|
||||
|
||||
/*!
|
||||
* \brief Compiles the provided regex pattern
|
||||
*
|
||||
* This automatically removes the existing compiled regex if already
|
||||
* present.
|
||||
*
|
||||
* If the NREX_THROW_ERROR was defined it would automatically throw a
|
||||
* runtime error nrex_compile_error if it encounters a problem when
|
||||
* parsing the pattern.
|
||||
*
|
||||
* \param The regex pattern
|
||||
* \return True if the pattern was succesfully compiled
|
||||
*/
|
||||
bool compile(const nrex_char* pattern);
|
||||
|
||||
/*!
|
||||
* \brief Uses the pattern to search through the provided string
|
||||
* \param str The text to search through. It only needs to be
|
||||
* null terminated if the end point is not provided.
|
||||
* This also determines the starting anchor.
|
||||
* \param captures The array of results to store the capture results.
|
||||
* The size of that array needs to be the same as the
|
||||
* size given in nrex::capture_size(). As it matches
|
||||
* the function fills the array with the results. 0 is
|
||||
* the result for the entire pattern, 1 and above
|
||||
* corresponds to the regex capture group if present.
|
||||
* \param offset The starting point of the search. This does not move
|
||||
* the starting anchor. Defaults to 0.
|
||||
* \param end The end point of the search. This also determines
|
||||
* the ending anchor. If a number less than the offset
|
||||
* is provided, the search would be done until null
|
||||
* termination. Defaults to -1.
|
||||
* \return True if a match was found. False otherwise.
|
||||
*/
|
||||
bool match(const nrex_char* str, nrex_result* captures, int offset = 0, int end = -1) const;
|
||||
};
|
||||
|
||||
#ifdef NREX_THROW_ERROR
|
||||
|
||||
#include <stdexcept>
|
||||
|
||||
class nrex_compile_error : std::runtime_error
|
||||
{
|
||||
public:
|
||||
nrex_compile_error(const char* message)
|
||||
: std::runtime_error(message)
|
||||
{
|
||||
}
|
||||
|
||||
~nrex_compile_error() throw()
|
||||
{
|
||||
}
|
||||
};
|
||||
|
||||
#endif
|
||||
|
||||
#endif // NREX_HPP
|
||||
12
drivers/nrex/nrex_config.h
Normal file
12
drivers/nrex/nrex_config.h
Normal file
|
|
@ -0,0 +1,12 @@
|
|||
// Godot-specific configuration
|
||||
// To use this, replace nrex_config.h
|
||||
|
||||
#include "core/os/memory.h"
|
||||
|
||||
#define NREX_UNICODE
|
||||
//#define NREX_THROW_ERROR
|
||||
|
||||
#define NREX_NEW(X) memnew(X)
|
||||
#define NREX_NEW_ARRAY(X, N) memnew_arr(X, N)
|
||||
#define NREX_DELETE(X) memdelete(X)
|
||||
#define NREX_DELETE_ARRAY(X) memdelete_arr(X)
|
||||
112
drivers/nrex/regex.cpp
Normal file
112
drivers/nrex/regex.cpp
Normal file
|
|
@ -0,0 +1,112 @@
|
|||
/*************************************************/
|
||||
/* regex.cpp */
|
||||
/*************************************************/
|
||||
/* This file is part of: */
|
||||
/* GODOT ENGINE */
|
||||
/*************************************************/
|
||||
/* Source code within this file is: */
|
||||
/* (c) 2007-2010 Juan Linietsky, Ariel Manzur */
|
||||
/* All Rights Reserved. */
|
||||
/*************************************************/
|
||||
|
||||
#include "regex.h"
|
||||
#include "nrex.hpp"
|
||||
#include "core/os/memory.h"
|
||||
|
||||
void RegEx::_bind_methods() {
|
||||
|
||||
ObjectTypeDB::bind_method(_MD("compile","pattern"),&RegEx::compile);
|
||||
ObjectTypeDB::bind_method(_MD("match","text","start","end"),&RegEx::match, DEFVAL(0), DEFVAL(-1));
|
||||
ObjectTypeDB::bind_method(_MD("get_capture","capture"),&RegEx::get_capture);
|
||||
ObjectTypeDB::bind_method(_MD("get_capture_list"),&RegEx::_bind_get_capture_list);
|
||||
|
||||
};
|
||||
|
||||
StringArray RegEx::_bind_get_capture_list() const {
|
||||
|
||||
StringArray ret;
|
||||
int count = get_capture_count();
|
||||
for (int i=0; i<count; i++) {
|
||||
|
||||
String c = get_capture(i);
|
||||
ret.push_back(c);
|
||||
};
|
||||
|
||||
return ret;
|
||||
|
||||
};
|
||||
|
||||
void RegEx::clear() {
|
||||
|
||||
text.clear();
|
||||
captures.clear();
|
||||
exp.reset();
|
||||
|
||||
};
|
||||
|
||||
bool RegEx::is_valid() const {
|
||||
|
||||
return exp.valid();
|
||||
|
||||
};
|
||||
|
||||
int RegEx::get_capture_count() const {
|
||||
|
||||
return exp.capture_size();
|
||||
}
|
||||
|
||||
String RegEx::get_capture(int capture) const {
|
||||
|
||||
ERR_FAIL_COND_V( get_capture_count() <= capture, String() );
|
||||
|
||||
return text.substr(captures[capture].start, captures[capture].length);
|
||||
|
||||
}
|
||||
|
||||
Error RegEx::compile(const String& p_pattern) {
|
||||
|
||||
clear();
|
||||
|
||||
exp.compile(p_pattern.c_str());
|
||||
|
||||
ERR_FAIL_COND_V( !exp.valid(), FAILED );
|
||||
|
||||
captures.resize(exp.capture_size());
|
||||
|
||||
return OK;
|
||||
|
||||
};
|
||||
|
||||
bool RegEx::match(const String& p_text, int p_start, int p_end) const {
|
||||
|
||||
|
||||
ERR_FAIL_COND_V( !exp.valid(), false );
|
||||
ERR_FAIL_COND_V( p_text.length() < p_start, false );
|
||||
ERR_FAIL_COND_V( p_text.length() < p_end, false );
|
||||
|
||||
bool res = exp.match(p_text.c_str(), &captures[0], p_start, p_end);
|
||||
|
||||
if (res) {
|
||||
text = p_text;
|
||||
return true;
|
||||
}
|
||||
text.clear();
|
||||
return false;
|
||||
|
||||
};
|
||||
|
||||
RegEx::RegEx(const String& p_pattern) {
|
||||
|
||||
compile(p_pattern);
|
||||
|
||||
};
|
||||
|
||||
RegEx::RegEx() {
|
||||
|
||||
};
|
||||
|
||||
RegEx::~RegEx() {
|
||||
|
||||
clear();
|
||||
|
||||
};
|
||||
47
drivers/nrex/regex.h
Normal file
47
drivers/nrex/regex.h
Normal file
|
|
@ -0,0 +1,47 @@
|
|||
/*************************************************/
|
||||
/* regex.h */
|
||||
/*************************************************/
|
||||
/* This file is part of: */
|
||||
/* GODOT ENGINE */
|
||||
/*************************************************/
|
||||
/* Source code within this file is: */
|
||||
/* (c) 2007-2010 Juan Linietsky, Ariel Manzur */
|
||||
/* All Rights Reserved. */
|
||||
/*************************************************/
|
||||
|
||||
#ifndef REGEX_H
|
||||
#define REGEX_H
|
||||
|
||||
#include "ustring.h"
|
||||
#include "vector.h"
|
||||
#include "core/reference.h"
|
||||
#include "nrex.hpp"
|
||||
|
||||
class RegEx : public Reference {
|
||||
|
||||
OBJ_TYPE(RegEx, Reference);
|
||||
|
||||
mutable String text;
|
||||
mutable Vector<nrex_result> captures;
|
||||
nrex exp;
|
||||
|
||||
protected:
|
||||
|
||||
static void _bind_methods();
|
||||
StringArray _bind_get_capture_list() const;
|
||||
|
||||
public:
|
||||
|
||||
void clear();
|
||||
bool is_valid() const;
|
||||
int get_capture_count() const;
|
||||
String get_capture(int capture) const;
|
||||
Error compile(const String& p_pattern);
|
||||
bool match(const String& p_text, int p_start = 0, int p_end = -1) const;
|
||||
|
||||
RegEx();
|
||||
RegEx(const String& p_pattern);
|
||||
~RegEx();
|
||||
};
|
||||
|
||||
#endif // REGEX_H
|
||||
Loading…
Add table
Add a link
Reference in a new issue