aabc2/KOS_qrcodes
1
0
Fork 0
forked from KolibriOS/kolibrios
Code Pull Requests Activity

tinypy: added re and random modules, not adapted for Kolibri yet.

Browse Source 
git-svn-id: svn://kolibrios.org@2043 a494cfbc-eb01-0410-851d-a64ba20cac60
This commit is contained in:
jaeger
2011-08-08 11:24:49 +00:00
parent 3653a07ac3
commit 6c55e4b3c3
8 changed files with 5344 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
programs/develop/tinypy/modules/random/init.c Normal file
View File

@@ -0,0 +1,52 @@
#include "random.c"
/*
* random_mod_init()
*
* random module initialization function
*/
void random_init(TP)
{
/*
* module dict for random
*/
tp_obj random_mod = tp_dict(tp);
/*
* bind functions to random module
*/
tp_set(tp, random_mod, tp_string("seed"), tp_fnc(tp, random_seed));
tp_set(tp, random_mod, tp_string("getstate"), tp_fnc(tp, random_getstate));
tp_set(tp, random_mod, tp_string("setstate"), tp_fnc(tp, random_setstate));
tp_set(tp, random_mod, tp_string("jumpahead"), tp_fnc(tp, random_jumpahead));
tp_set(tp, random_mod, tp_string("random"), tp_fnc(tp, random_random));
/*
* bind usual distribution random variable generator
*/
tp_set(tp, random_mod, tp_string("uniform"), tp_fnc(tp, random_uniform));
tp_set(tp, random_mod, tp_string("normalvariate"), tp_fnc(tp, random_normalvariate));
tp_set(tp, random_mod, tp_string("lognormvariate"), tp_fnc(tp, random_lognormvariate));
tp_set(tp, random_mod, tp_string("expovariate"), tp_fnc(tp, random_expovariate));
tp_set(tp, random_mod, tp_string("vonmisesvariate"), tp_fnc(tp, random_vonmisesvariate));
tp_set(tp, random_mod, tp_string("gammavariate"), tp_fnc(tp, random_gammavariate));
tp_set(tp, random_mod, tp_string("betavariate"), tp_fnc(tp, random_betavariate));
tp_set(tp, random_mod, tp_string("paretovariate"), tp_fnc(tp, random_paretovariate));
tp_set(tp, random_mod, tp_string("weibullvariate"), tp_fnc(tp, random_weibullvariate));
tp_set(tp, random_mod, tp_string("randrange"), tp_fnc(tp, random_randrange));
tp_set(tp, random_mod, tp_string("randint"), tp_fnc(tp, random_randint));
tp_set(tp, random_mod, tp_string("choice"), tp_fnc(tp, random_choice));
tp_set(tp, random_mod, tp_string("shuffle"), tp_fnc(tp, random_shuffle));
/*
* bind special attributes to random module
*/
tp_set(tp, random_mod, tp_string("__doc__"), tp_string("Random variable generators."));
tp_set(tp, random_mod, tp_string("__name__"), tp_string("random"));
tp_set(tp, random_mod, tp_string("__file__"), tp_string(__FILE__));
/*
* bind random module to tinypy modules[]
*/
tp_set(tp, tp->modules, tp_string("random"), random_mod);
}

1107
programs/develop/tinypy/modules/random/random.c Normal file
View File

File diff suppressed because it is too large Load Diff

176
programs/develop/tinypy/modules/random/tests.py Normal file
View File

@@ -0,0 +1,176 @@
#!/usr/bin/env python
import random
#from math import log, exp, sqrt, pi
def test_seed_state():
"""test seed() and getstate()/setstate()
"""
# random ought to be able to deal with seeds in any form, of follows.
# following code shouldn't cause an exception.
random.seed()
random.seed(0)
random.seed(-1)
random.seed(0.1)
random.seed(-0.1)
random.seed("a")
random.seed("abc")
random.seed("abcd")
random.seed("fasdfasdfasdfadgaldhgldahlgahdlghadlgladh")
random.seed("lxhlh90yowhldshlgah;")
# state1 and state2 should be different for different seeds
random.seed(1)
state1 = random.getstate()
random.seed(2)
state2 = random.getstate()
rep = 0
for ind in range(len(state1)):
elem1 = state1[ind]
elem2 = state2[ind]
if (elem1 == elem2): rep += 1
if (rep > len(state1) / 2):
print("rep = ", rep, "len(state1) = ", len(state1))
raise "state1 and state2 should be different"
# for the same seeds, state1 and state2 should be the same
random.seed(100)
state1 = random.getstate()
random.seed(100)
state2 = random.getstate()
rep = 0
for ind in range(len(state1)):
elem1 = state1[ind]
elem2 = state2[ind]
if (elem1 == elem2): rep += 1
if (rep != len(state1)):
raise "state1 and state2 should be the same"
def test_jumpahead():
"""jumpahead will change the pseudo-number generator's internal state
"""
random.seed()
state1 = random.getstate()
random.jumpahead(20)
state2 = random.getstate()
rep = 0
for ind in range(len(state1)):
elem1 = state1[ind]
elem2 = state2[ind]
if (elem1 == elem2): rep += 1
if (rep > len(state1) / 2):
raise "state1 and state2 can't be the same"
def test_setstate():
"""
"""
random.seed()
oldState = random.getstate()
oldRandSeq = [random.random() for i in range(10)]
random.setstate(oldState)
newRandSeq = [random.random() for i in range(10)]
rep = 0
for ind in range(len(oldRandSeq)):
elem1 = oldRandSeq[ind]
elem2 = newRandSeq[ind]
if (elem1 == elem2): rep += 1
if (rep != len(oldRandSeq)):
raise "oldRandSeq and newRandSeq should be the same"
def test_random():
"""generate a random number list
"""
x = [random.random() for i in range(100)]
def test_distribution():
"""these lines are borrowed from python, they shouldn't
cause any exception.
"""
g = random
g.uniform(1,10)
g.paretovariate(1.0)
g.expovariate(1.0)
g.weibullvariate(1.0, 1.0)
g.normalvariate(0.0, 1.0)
g.lognormvariate(0.0, 1.0)
g.vonmisesvariate(0.0, 1.0)
g.gammavariate(0.01, 1.0)
g.gammavariate(1.0, 1.0)
g.gammavariate(200.0, 1.0)
g.betavariate(3.0, 3.0)
def test_randrange():
"""these input to randrange() shouldn't cause any exception.
"""
random.randrange(100000)
random.randrange(-100000)
random.randrange(0)
random.randrange(-10.2)
random.randrange(-10, 10)
random.randrange(2, 1000)
random.randrange(0, 1)
random.randrange(-1, 0)
random.randrange(10, 2000, 2)
random.randrange(-2000, 100, 5)
random.randrange(-1000.3, 1000.7, 2)
def test_randint():
"""for any valid pair (a, b), randint(a, b) should lay between [a, b]
"""
for i in range(1000):
r = random.randint(-10000, 10000)
if (-10000 <= r <= 10000): continue
else: raise "error: random.randint()"
def test_choice():
"""random.choice() should be able to deal with string, list.
"""
S = "abcdefg123*@#$%)("
L = [1, 2, 3, -1, 0.2, -0.1, -10000, "cyc"]
if random.choice(S) not in S:
raise "error: random.choice(S)"
if random.choice(L) not in L:
raise "error: random.choice(L)"
def test_shuffle():
"""test random.shuffle() on list. since string is not writable in-place,
random.shuffle() can not be applied on string.
Note: to copy items from a list to a new list, must use syntax like:
newList = oldList[:]
if use syntax like: newList = oldList, newList is just an alias of oldList.
"""
oldL = [1, 2, 3, -1, 0.2, -0.1, -10000, "cyc"]
newL = oldL[:]
random.shuffle(newL)
rep = 0
for ind in range(len(oldL)):
elem1 = oldL[ind]
elem2 = newL[ind]
if (elem1 == elem2): rep += 1
if (rep > len(oldL) / 2):
raise "oldL and newL shouldn't be the same"
def test_53_bits_per_float():
pass
def main():
test_seed_state()
test_jumpahead()
test_setstate()
test_random()
test_distribution()
test_randrange()
test_randint()
test_choice()
test_shuffle()
test_53_bits_per_float()
print("#OK")
if __name__ == '__main__':
main()

710
programs/develop/tinypy/modules/re/init.c Normal file
View File

@@ -0,0 +1,710 @@
/*
* regular expression module
*
* Important Note: do not support group name index
*
* $Id$
*/
#include <stdio.h>
#include <assert.h>
#include "regexpr.c"
/* tinypy API to be use in this unit */
extern tp_obj tp_data(TP,int magic,void *v);
extern tp_obj tp_object_new(TP);
extern tp_obj tp_object(TP);
extern tp_obj tp_method(TP,tp_obj self,tp_obj v(TP));
extern tp_obj tp_string_copy(TP, const char *s, int n);
extern tp_obj tp_list(TP);
extern tp_obj tp_copy(TP);
/* last error message */
static const char * LastError = NULL;
/* lower level regex object */
typedef struct {
struct re_pattern_buffer re_patbuf; /* The compiled expression */
struct re_registers re_regs; /* The registers from the last match */
char re_fastmap[256]; /* Storage for fastmap */
unsigned char *re_translate; /* String object for translate table */
unsigned char *re_lastok; /* String object last matched/searched */
/* supplementary */
int re_errno; /* error num */
int re_syntax; /* syntax */
} regexobject;
/* local declarations */
static regexobject* getre(TP, tp_obj rmobj);
static tp_obj match_obj_group(TP);
static tp_obj match_obj_groups(TP);
static tp_obj match_obj_start(TP);
static tp_obj match_obj_end(TP);
static tp_obj match_obj_span(TP);
/*
* helper function: return lower level regex object
* rmobj - regex or match object
*/
static regexobject * getre(TP, tp_obj rmobj)
{
tp_obj reobj_data = tp_get(tp, rmobj, tp_string("__data__"));
regexobject *re = NULL;
/* validate magic */
if (reobj_data.data.magic != sizeof(regexobject)) {
LastError = "broken regex object";
return (NULL);
}
re = (regexobject*)reobj_data.data.val;
assert(re);
return (re);
}
/*
* derive match object from regex object
*/
static tp_obj match_object(TP, tp_obj reobj)
{
tp_obj mo = tp_object(tp); /* match object */
tp_obj redata; /* regex object data */
tp_obj madata; /* match object data */
regexobject *re = NULL; /* lower level regex object */
redata = tp_get(tp, reobj, tp_string("__data__"));
re = (regexobject *)redata.data.val;
assert(re);
madata = tp_data(tp, (int)sizeof(regexobject), re);
tp_set(tp, mo, tp_string("group"), tp_method(tp, mo, match_obj_group));
tp_set(tp, mo, tp_string("groups"), tp_method(tp, mo, match_obj_groups));
tp_set(tp, mo, tp_string("start"), tp_method(tp, mo, match_obj_start));
tp_set(tp, mo, tp_string("end"), tp_method(tp, mo, match_obj_end));
tp_set(tp, mo, tp_string("span"), tp_method(tp, mo, match_obj_span));
tp_set(tp, mo, tp_string("__data__"), madata);
return (mo);
}
/*
* FUNC: regexobj.search(str[,pos=0])
* self - regex object
* str - string to be searched
* pos - optional starting offset
*
* RETURN:
* match object - when matched
* None - not matched
*/
static tp_obj regex_obj_search(TP)
{
tp_obj self = TP_OBJ(); /* regex object */
tp_obj str = TP_STR();
tp_obj pos = TP_DEFAULT(tp_number(0));
tp_obj maobj; /* match object */
regexobject *re = NULL;
int r = -2; /* -2 indicate exception */
int range;
if (pos.number.val < 0 || pos.number.val > str.string.len) {
LastError = "search offset out of range";
goto exception;
}
range = str.string.len - pos.number.val;
re = getre(tp, self);
re->re_lastok = NULL;
r = re_search(&re->re_patbuf, (unsigned char *)str.string.val,
str.string.len, pos.number.val, range, &re->re_regs);
/* cannot match pattern */
if (r == -1)
goto notfind;
/* error occurred */
if (r == -2)
goto exception;
/* matched */
re->re_lastok = (unsigned char *)str.string.val;
/* match obj */
maobj = match_object(tp, self);
return (maobj);
notfind:
re->re_lastok = NULL;
return (tp_None);
exception:
re->re_lastok = NULL;
tp_raise(tp_None, tp_string("regex search error"));
}
/*
* FUNC: regexobj.match(str[,pos=0])
* self - regex object
* str - string to be matched
* pos - optional starting position
*
* RETURN:
* match object - when matched
* None - not matched
*/
static tp_obj regex_obj_match(TP)
{
tp_obj self = TP_OBJ(); /* regex object */
tp_obj str = TP_STR();
tp_obj pos = TP_DEFAULT(tp_number(0));
tp_obj maobj; /* match object */
regexobject *re = NULL;
int r = -2; /* -2 indicate exception */
re = getre(tp, self);
re->re_lastok = NULL;
r = re_match(&re->re_patbuf, (unsigned char *)str.string.val,
str.string.len, pos.number.val, &re->re_regs);
/* cannot match pattern */
if (r == -1)
goto nomatch;
/* error occurred */
if (r == -2)
goto exception;
/* matched */
re->re_lastok = (unsigned char *)str.string.val;
/* match obj */
maobj = match_object(tp, self);
return (maobj);
nomatch:
re->re_lastok = NULL;
return (tp_None);
exception:
re->re_lastok = NULL;
tp_raise(tp_None, tp_string("regex match error"));
}
/*
* regex object split()
* self - regex object
* restr - regex string
* maxsplit - max split field, default 0, mean no limit
*/
static tp_obj regex_obj_split(TP)
{
tp_obj self = TP_OBJ(); /* regex object */
tp_obj restr = TP_OBJ(); /* string */
tp_obj maxsplit = TP_DEFAULT(tp_number(0));
tp_obj maobj; /* match object */
regexobject *re = NULL; /* lower level regex object */
tp_obj result = tp_list(tp);
tp_obj grpstr; /* group string */
int slen; /* string length */
int srchloc; /* search location */
/* maxsplit == 0 means no limit */
if ((int)maxsplit.number.val == 0)
maxsplit.number.val = RE_NREGS;
assert(maxsplit.number.val > 0);
srchloc = 0;
slen = strlen((char *)restr.string.val);
do {
/* generate a temp match object */
tp_params_v(tp, 3, self, restr, tp_number(srchloc));
maobj = regex_obj_search(tp);
if (!tp_bool(tp, maobj))
break;
re = getre(tp, maobj);
if (re->re_lastok == NULL) {
tp_raise(tp_None, tp_string("no match for split()"));
}
/* extract fields */
if ((int)maxsplit.number.val > 0) {
int start = re->re_regs.start[0];
int end = re->re_regs.end[0];
/*printf("%s:start(%d),end(%d)\n", __func__, start, end);*/
if (start < 0 || end < 0)
break;
grpstr = tp_string_copy(tp,
(const char *)re->re_lastok + srchloc, start - srchloc);
if (tp_bool(tp, grpstr)) {
tp_set(tp, result, tp_None, grpstr);
maxsplit.number.val--;
}
srchloc = end;
}
} while (srchloc < slen && (int)maxsplit.number.val > 0);
/* collect remaining string, if necessary */
if (srchloc < slen) {
grpstr = tp_string_copy(tp,
(const char *)restr.string.val + srchloc, slen - srchloc);
if (tp_bool(tp, grpstr))
tp_set(tp, result, tp_None, grpstr);
}
return (result);
}
/*
* regex object findall()
* self - regex object
* restr - regex string
* pos - starting position, default 0
*/
static tp_obj regex_obj_findall(TP)
{
tp_obj self = TP_OBJ(); /* regex object */
tp_obj restr = TP_OBJ(); /* string */
tp_obj pos = TP_DEFAULT(tp_number(0));
tp_obj maobj; /* match object */
regexobject *re = NULL; /* lower level regex object */
tp_obj result = tp_list(tp);
tp_obj grpstr; /* group string */
int slen; /* string length */
int srchloc; /* search location */
srchloc = (int)pos.number.val;
slen = strlen((char *)restr.string.val);
if (srchloc < 0 || srchloc >= slen)
tp_raise(tp_None, tp_string("starting position out of range"));
do {
/* generate a temp match object */
tp_params_v(tp, 3, self, restr, tp_number(srchloc));
maobj = regex_obj_search(tp);
if (!tp_bool(tp, maobj))
break;
re = getre(tp, maobj);
if (re->re_lastok == NULL) {
tp_raise(tp_None, tp_string("no match for findall()"));
}
/* extract fields */
if (srchloc < slen) {
int start = re->re_regs.start[0];
int end = re->re_regs.end[0];
/*printf("%s:start(%d),end(%d)\n", __func__, start, end);*/
if (start < 0 || end < 0)
break;
grpstr = tp_string_copy(tp,
(const char *)re->re_lastok + start, end - start);
if (tp_bool(tp, grpstr)) {
tp_set(tp, result, tp_None, grpstr);
}
srchloc = end;
}
} while (srchloc < slen);
return (result);
}
/*
* FUNC: matchobj.group([group1, ...])
* self - match object
* args - optional group indices, default 0
*
* return specified group.
*/
static tp_obj match_obj_group(TP)
{
tp_obj self = TP_OBJ(); /* match object */
tp_obj grpidx; /* a group index */
regexobject *re = NULL;
int indices[RE_NREGS];
int start;
int end;
int i;
int single = 0; /* single group index? */
tp_obj result;
/* get lower level regex object representation */
re = getre(tp, self);
if (re->re_lastok == NULL)
tp_raise(tp_None,
tp_string("group() only valid after successful match/search"));
for (i = 0; i < RE_NREGS; i++)
indices[i] = -1;
/*
* if no group index provided, supply default group index 0; else
* fill in indices[] with provided group index list.
*/
if (tp->params.list.val->len == 0) {
indices[0] = 0;
single = 1;
} else if (tp->params.list.val->len == 1) {
indices[0] = (int)TP_NUM();
single = 1;
} else {
i = 0;
TP_LOOP(grpidx)
if (grpidx.number.val < 0 || grpidx.number.val > RE_NREGS)
tp_raise(tp_None, tp_string("group() grpidx out of range"));
indices[i++] = (int)grpidx.number.val;
TP_END
}
/* generate result string list */
result = tp_list(tp);
for (i = 0; i < RE_NREGS && indices[i] >= 0; i++) {
tp_obj grpstr;
start = re->re_regs.start[indices[i]];
end = re->re_regs.end[indices[i]];
if (start < 0 || end < 0) {
grpstr = tp_None;
} else {
grpstr = tp_string_copy(tp, (const char *)re->re_lastok + start,
end - start);
}
tp_set(tp, result, tp_None, grpstr);
}
return (single ? tp_get(tp, result, tp_number(0)) : result);
}
/*
* FUNC: matchobj.groups()
* self - match object.
* return all groups.
* Note: CPython allow a 'default' argument, but we disallow it.
*/
static tp_obj match_obj_groups(TP)
{
tp_obj self = TP_OBJ(); /* match object */
regexobject *re = NULL;
int start;
int end;
int i;
tp_obj result = tp_list(tp);
re = getre(tp, self);
if (re->re_lastok == NULL) {
tp_raise(tp_None,
tp_string("groups() only valid after successful match/search"));
}
for (i = 1; i < RE_NREGS; i++) {
start = re->re_regs.start[i];
end = re->re_regs.end[i];
if (start < 0 || end < 0)
break;
tp_obj grpstr = tp_string_copy(tp,
(const char *)re->re_lastok + start, end - start);
if (tp_bool(tp, grpstr))
tp_set(tp, result, tp_None, grpstr);
}
return (result);
}
/*
* FUNC: matchobj.start([group])
* self - match object
* group - group index
* return starting position of matched 'group' substring.
*/
static tp_obj match_obj_start(TP)
{
tp_obj self = TP_OBJ(); /* match object */
tp_obj group = TP_DEFAULT(tp_number(0)); /* group */
regexobject *re = NULL;
int start;
re = getre(tp, self);
if (re->re_lastok == NULL) {
tp_raise(tp_None,
tp_string("start() only valid after successful match/search"));
}
if (group.number.val < 0 || group.number.val > RE_NREGS)
tp_raise(tp_None, tp_string("IndexError: group index out of range"));
start = re->re_regs.start[(int)group.number.val];
return (tp_number(start));
}
/*
* FUNC: matchobj.end([group])
* self - match object
* group - group index
* return ending position of matched 'group' substring.
*/
static tp_obj match_obj_end(TP)
{
tp_obj self = TP_OBJ(); /* match object */
tp_obj group = TP_DEFAULT(tp_number(0)); /* group */
regexobject *re = NULL;
int end;
re = getre(tp, self);
if (re->re_lastok == NULL) {
tp_raise(tp_None,
tp_string("end() only valid after successful match/search"));
}
if (group.number.val < 0 || group.number.val > RE_NREGS)
tp_raise(tp_None, tp_string("IndexError: group index out of range"));
end = re->re_regs.end[(int)group.number.val];
return (tp_number(end));
}
/*
* FUNC: matchobj.span([group])
* self - match object
* group - group index
* return [start,end] position pair of matched 'group' substring.
*/
static tp_obj match_obj_span(TP)
{
tp_obj self = TP_OBJ(); /* match object */
tp_obj group = TP_DEFAULT(tp_number(0)); /* group */
regexobject *re = NULL;
int start;
int end;
tp_obj result;
re = getre(tp, self);
if (re->re_lastok == NULL) {
tp_raise(tp_None,
tp_string("span() only valid after successful match/search"));
}
if (group.number.val < 0 || group.number.val > RE_NREGS)
tp_raise(tp_None, tp_string("IndexError: group index out of range"));
start = re->re_regs.start[(int)group.number.val];
end = re->re_regs.end[(int)group.number.val];
result = tp_list(tp);
tp_set(tp, result, tp_None, tp_number(start));
tp_set(tp, result, tp_None, tp_number(end));
return (result);
}
/*
* compile out a re object
* repat - regex pattern
* resyn - regex syntax
*/
static tp_obj regex_compile(TP)
{
char *error = NULL;
char const *pat = NULL;
int size = 0;
tp_obj reobj_data;
tp_obj repat = TP_TYPE(TP_STRING); /* pattern */
tp_obj resyn = TP_DEFAULT(tp_number(RE_SYNTAX_EMACS)); /* syntax */
tp_obj reobj; /* regex object */
regexobject *re;
/*
* create regex object, its parent is builtin 'object'
*/
reobj = tp_object(tp);
re = (regexobject *)malloc(sizeof(regexobject));
if (!re) {
error = "malloc lower level regex object failed";
goto finally;
}
re->re_patbuf.buffer = NULL;
re->re_patbuf.allocated = 0;
re->re_patbuf.fastmap = (unsigned char *)re->re_fastmap;
re->re_patbuf.translate = NULL;
re->re_translate = NULL;
re->re_lastok = NULL;
re->re_errno = 0;
re->re_syntax = (int)resyn.number.val;
pat = repat.string.val;
size = repat.string.len;
error = re_compile_pattern((unsigned char *)pat, size, &re->re_patbuf);
if (error != NULL) {
LastError = error;
goto finally;
}
/* regexobject's size as magic */
reobj_data = tp_data(tp, (int)sizeof(regexobject), re);
/*
* bind to regex object
*/
tp_set(tp, reobj, tp_string("search"),
tp_method(tp, reobj, regex_obj_search));
tp_set(tp, reobj, tp_string("match"),
tp_method(tp, reobj, regex_obj_match));
tp_set(tp, reobj, tp_string("split"),
tp_method(tp, reobj, regex_obj_split));
tp_set(tp, reobj, tp_string("findall"),
tp_method(tp, reobj, regex_obj_findall));
tp_set(tp, reobj, tp_string("__data__"), reobj_data);
tp_set(tp, reobj, tp_string("__name__"),
tp_string("regular expression object"));
tp_set(tp, reobj, tp_string("__doc__"), tp_string(
"regular expression object, support methods:\n"
"search(str[,pos=0])-search 'str' from 'pos'\n"
"match(str[,pos=0]) -match 'str' from 'pos'\n"
));
return (reobj);
finally:
tp_raise(tp_None, tp_string(error));
}
/*
* module level search()
*/
static tp_obj regex_search(TP)
{
tp_obj repat = TP_OBJ(); /* pattern */
tp_obj restr = TP_OBJ(); /* string */
tp_obj resyn = TP_DEFAULT(tp_number(RE_SYNTAX_EMACS));
tp_obj reobj; /* regex object */
tp_obj maobj; /* match object */
/* compile out regex object */
tp_params_v(tp, 2, repat, resyn);
reobj = regex_compile(tp);
/* call r.search() */
tp_params_v(tp, 3, reobj, restr, tp_number(0));
maobj = regex_obj_search(tp);
return (maobj);
}
/*
* module level match()
*/
static tp_obj regex_match(TP)
{
tp_obj repat = TP_OBJ(); /* pattern */
tp_obj restr = TP_OBJ(); /* string */
tp_obj resyn = TP_DEFAULT(tp_number(RE_SYNTAX_EMACS));
tp_obj reobj; /* regex object */
tp_obj maobj; /* match object */
/* compile out regex object */
tp_params_v(tp, 2, repat, resyn);
reobj = regex_compile(tp);
/* call r.search() */
tp_params_v(tp, 3, reobj, restr, tp_number(0));
maobj = regex_obj_match(tp);
return (maobj);
}
/*
* module level split()
* repat - regex pattern
* restr - regex string
* maxsplit - max split field, default 0, mean no limit
*/
static tp_obj regex_split(TP)
{
tp_obj repat = TP_OBJ(); /* pattern */
tp_obj restr = TP_OBJ(); /* string */
tp_obj maxsplit = TP_DEFAULT(tp_number(0));
tp_obj reobj; /* regex object */
/* generate a temp regex object */
tp_params_v(tp, 2, repat, tp_number(RE_SYNTAX_EMACS));
reobj = regex_compile(tp);
tp_params_v(tp, 3, reobj, restr, maxsplit);
return regex_obj_split(tp);
}
/*
* module level findall()
* repat - regex pattern
* restr - regex string
* resyn - regex syntax, optional, default RE_SYNTAX_EMAC
*/
static tp_obj regex_findall(TP)
{
tp_obj repat = TP_OBJ(); /* pattern */
tp_obj restr = TP_OBJ(); /* string */
tp_obj resyn = TP_DEFAULT(tp_number(RE_SYNTAX_EMACS));
tp_obj reobj; /* regex object */
/* generate a temp regex object */
tp_params_v(tp, 2, repat, resyn);
reobj = regex_compile(tp);
tp_params_v(tp, 2, reobj, restr);
return regex_obj_findall(tp);
}
/*
* re mod can only support 'set_syntax', 'get_syntax', and 'compile' functions,
* 'compile' function will return a 'reobj', and this 'reobj' will support
* methods 'search', 'match', 'group', 'groupall', el al.
*/
void re_init(TP)
{
/*
* module dict for re
*/
tp_obj re_mod = tp_dict(tp);
/*
* bind to re module
*/
tp_set(tp, re_mod, tp_string("compile"), tp_fnc(tp, regex_compile));
tp_set(tp, re_mod, tp_string("search"), tp_fnc(tp, regex_search));
tp_set(tp, re_mod, tp_string("match"), tp_fnc(tp, regex_match));
tp_set(tp, re_mod, tp_string("split"), tp_fnc(tp, regex_split));
tp_set(tp, re_mod, tp_string("findall"), tp_fnc(tp, regex_findall));
tp_set(tp, re_mod, tp_string("AWK_SYNTAX"), tp_number(RE_SYNTAX_AWK));
tp_set(tp, re_mod, tp_string("EGREP_SYNTAX"), tp_number(RE_SYNTAX_EGREP));
tp_set(tp, re_mod, tp_string("GREP_SYNTAX"), tp_number(RE_SYNTAX_GREP));
tp_set(tp, re_mod, tp_string("EMACS_SYNTAX"), tp_number(RE_SYNTAX_EMACS));
/*
* bind special attibutes to re module
*/
tp_set(tp, re_mod, tp_string("__name__"),
tp_string("regular expression module"));
tp_set(tp, re_mod, tp_string("__file__"), tp_string(__FILE__));
tp_set(tp, re_mod, tp_string("__doc__"),
tp_string("simple regular express implementation"));
/*
* bind regex module to tinypy modules[]
*/
tp_set(tp, tp->modules, tp_string("re"), re_mod);
}

2124
programs/develop/tinypy/modules/re/regexpr.c Normal file
View File

File diff suppressed because it is too large Load Diff

160
programs/develop/tinypy/modules/re/regexpr.h Normal file
View File

@@ -0,0 +1,160 @@
/*
* -*- mode: c-mode; c-file-style: python -*-
*/
#ifndef Py_REGEXPR_H
#define Py_REGEXPR_H
#ifdef __cplusplus
extern "C" {
#endif
/*
* regexpr.h
*
* Author: Tatu Ylonen <ylo@ngs.fi>
*
* Copyright (c) 1991 Tatu Ylonen, Espoo, Finland
*
* Permission to use, copy, modify, distribute, and sell this software
* and its documentation for any purpose is hereby granted without fee,
* provided that the above copyright notice appear in all copies. This
* software is provided "as is" without express or implied warranty.
*
* Created: Thu Sep 26 17:15:36 1991 ylo
* Last modified: Mon Nov 4 15:49:46 1991 ylo
*/
/* $Id$ */
#ifndef REGEXPR_H
#define REGEXPR_H
#define RE_NREGS 100 /* number of registers available */
typedef struct re_pattern_buffer
{
unsigned char *buffer; /* compiled pattern */
int allocated; /* allocated size of compiled pattern */
int used; /* actual length of compiled pattern */
unsigned char *fastmap; /* fastmap[ch] is true if ch can start pattern */
unsigned char *translate; /* translation to apply during compilation/matching */
unsigned char fastmap_accurate; /* true if fastmap is valid */
unsigned char can_be_null; /* true if can match empty string */
unsigned char uses_registers; /* registers are used and need to be initialized */
int num_registers; /* number of registers used */
unsigned char anchor; /* anchor: 0=none 1=begline 2=begbuf */
} *regexp_t;
typedef struct re_registers
{
int start[RE_NREGS]; /* start offset of region */
int end[RE_NREGS]; /* end offset of region */
} *regexp_registers_t;
/* bit definitions for syntax */
#define RE_NO_BK_PARENS 1 /* no quoting for parentheses */
#define RE_NO_BK_VBAR 2 /* no quoting for vertical bar */
#define RE_BK_PLUS_QM 4 /* quoting needed for + and ? */
#define RE_TIGHT_VBAR 8 /* | binds tighter than ^ and $ */
#define RE_NEWLINE_OR 16 /* treat newline as or */
#define RE_CONTEXT_INDEP_OPS 32 /* ^$?*+ are special in all contexts */
#define RE_ANSI_HEX 64 /* ansi sequences (\n etc) and \xhh */
#define RE_NO_GNU_EXTENSIONS 128 /* no gnu extensions */
#define TP_RE_NOERR 0
#define TP_RE_UNKNOWN_OPCODE (-1)
#define TP_RE_JUMP_OUT_BOUNDS 1
#define TP_RE_QUOTE_ERR 2
/* definitions for some common regexp styles */
#define RE_SYNTAX_AWK (RE_NO_BK_PARENS|RE_NO_BK_VBAR|RE_CONTEXT_INDEP_OPS)
#define RE_SYNTAX_EGREP (RE_SYNTAX_AWK|RE_NEWLINE_OR)
#define RE_SYNTAX_GREP (RE_BK_PLUS_QM|RE_NEWLINE_OR)
#define RE_SYNTAX_EMACS 0
#define Sword 1
#define Swhitespace 2
#define Sdigit 4
#define Soctaldigit 8
#define Shexdigit 16
/* Rename all exported symbols to avoid conflicts with similarly named
symbols in some systems' standard C libraries... */
#define re_syntax _Py_re_syntax
#define re_syntax_table _Py_re_syntax_table
#define re_compile_initialize _Py_re_compile_initialize
#define re_set_syntax _Py_re_set_syntax
#define re_compile_pattern _Py_re_compile_pattern
#define re_match _Py_re_match
#define re_search _Py_re_search
#define re_compile_fastmap _Py_re_compile_fastmap
#define re_comp _Py_re_comp
#define re_exec _Py_re_exec
#ifdef HAVE_PROTOTYPES
extern int re_syntax;
/* This is the actual syntax mask. It was added so that Python could do
* syntax-dependent munging of patterns before compilation. */
extern unsigned char re_syntax_table[256];
void re_compile_initialize(void);
int re_set_syntax(int syntax);
/* This sets the syntax to use and returns the previous syntax. The
* syntax is specified by a bit mask of the above defined bits. */
char *re_compile_pattern(unsigned char *regex, int regex_size, regexp_t compiled);
/* This compiles the regexp (given in regex and length in regex_size).
* This returns NULL if the regexp compiled successfully, and an error
* message if an error was encountered. The buffer field must be
* initialized to a memory area allocated by malloc (or to NULL) before
* use, and the allocated field must be set to its length (or 0 if
* buffer is NULL). Also, the translate field must be set to point to a
* valid translation table, or NULL if it is not used. */
int re_match(regexp_t compiled, unsigned char *string, int size, int pos,
regexp_registers_t old_regs);
/* This tries to match the regexp against the string. This returns the
* length of the matched portion, or -1 if the pattern could not be
* matched and -2 if an error (such as failure stack overflow) is
* encountered. */
int re_search(regexp_t compiled, unsigned char *string, int size, int startpos,
int range, regexp_registers_t regs);
/* This searches for a substring matching the regexp. This returns the
* first index at which a match is found. range specifies at how many
* positions to try matching; positive values indicate searching
* forwards, and negative values indicate searching backwards. mstop
* specifies the offset beyond which a match must not go. This returns
* -1 if no match is found, and -2 if an error (such as failure stack
* overflow) is encountered. */
void re_compile_fastmap(regexp_t compiled);
/* This computes the fastmap for the regexp. For this to have any effect,
* the calling program must have initialized the fastmap field to point
* to an array of 256 characters. */
#else /* HAVE_PROTOTYPES */
extern int re_syntax;
extern unsigned char re_syntax_table[256];
void re_compile_initialize();
int re_set_syntax();
char *re_compile_pattern();
int re_match();
int re_search();
void re_compile_fastmap();
#endif /* HAVE_PROTOTYPES */
#endif /* REGEXPR_H */
#ifdef __cplusplus
}
#endif
#endif /* !Py_REGEXPR_H */

648
programs/develop/tinypy/modules/re/tests.py Normal file
View File

@@ -0,0 +1,648 @@
"""
test case for re module
"""
import re
import testsuite
SUCCEED, FAIL, SYNTAX_ERROR = range(3)
def RAISE():
raise("testing failed")
def main():
#print("begin re tests")
assert(re.__name__ != None)
assert(re.__doc__ != None)
assert(re.__file__ != None)
test_re_obj_search()
test_re_obj_match()
test_re_mod_search()
test_re_mod_match()
test_re_obj_split()
test_re_mod_split()
test_re_obj_findall()
test_re_mod_findall()
test_mat_obj_groups()
test_mat_obj_start()
test_mat_obj_end()
test_mat_obj_span()
print("#OK: re tests passed")
def test_re_obj_search(verbose = None):
"""
some tests borrowed from cpython
testing re.compile(), reobj.search(), and matobj.group()
"""
regex_tests = testsuite.search_regex_tests
for t in regex_tests:
pattern=s=outcome=repl=expected=None
if len(t)==5:
pattern, s, outcome, repl, expected = t
elif len(t)==3:
pattern, s, outcome = t
else:
raise ('Test tuples should have 3 or 5 fields',t)
try:
obj=re.compile(pattern)
except:
if outcome==SYNTAX_ERROR: continue # Expected a syntax error
else:
# Regex syntax errors aren't yet reported, so for
# the official test suite they'll be quietly ignored.
pass
try:
matobj=obj.search(s)
except:
print('=== Unexpected exception:', obj, matobj, pattern, s)
RAISE()
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
pass
elif outcome==FAIL:
if matobj==None: pass # No match, as expected
else: print('=== Succeeded incorrectly', obj, matobj, pattern, s)
elif outcome==SUCCEED:
if matobj!=None:
# Matched, as expected, so now we compute the
# result string and compare it to our expected result.
found=matobj.group(0)
repl = repl.replace("found", str(found))
for i in range(1,11):
if "g"+str(i) in repl:
gi = str(matobj.group(i))
repl = repl.replace("g"+str(i), gi)
if len(t) == 5:
repl = repl.replace('+', '')
repl = repl.replace('\"', '')
if repl!=expected:
print( '=== grouping error', t,
str(repl)+' should be '+str(expected))
RAISE()
else:
print ('=== Failed incorrectly', t)
def test_re_obj_match(verbose = None):
"""
some tests borrowed from cpython
testing re.compile(), reobj.match() and matobj.group()
"""
regex_tests = testsuite.match_regex_tests
for t in regex_tests:
pattern=s=outcome=repl=expected=None
if len(t)==5:
pattern, s, outcome, repl, expected = t
elif len(t)==3:
pattern, s, outcome = t
else:
raise ('Test tuples should have 3 or 5 fields',t)
try:
obj=re.compile(pattern)
except:
if outcome==SYNTAX_ERROR: continue # Expected a syntax error
else:
# Regex syntax errors aren't yet reported, so for
# the official test suite they'll be quietly ignored.
pass
try:
matobj=obj.match(s)
except:
print('=== Unexpected exception:', obj, matobj, pattern, s)
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
pass
elif outcome==FAIL:
if matobj==None: pass # No match, as expected
else: print('=== Succeeded incorrectly', obj, matobj, pattern, s)
elif outcome==SUCCEED:
if matobj!=None:
# Matched, as expected, so now we compute the
# result string and compare it to our expected result.
found=matobj.group(0)
repl = repl.replace("found", str(found))
for i in range(1,11):
if "g"+str(i) in repl:
gi = str(matobj.group(i))
repl = repl.replace("g"+str(i), gi)
if len(t) == 5:
repl = repl.replace('+', '')
repl = repl.replace('\"', '')
if repl!=expected:
print( '=== grouping error', t,
str(repl)+' should be '+str(expected))
RAISE()
else:
print ('=== Failed incorrectly', obj, matobj, pattern, s)
def test_re_mod_search(verbose = None):
"""
some tests borrowed from cpython
testing re.search(), and matobj.group()
"""
regex_tests = testsuite.search_regex_tests
for t in regex_tests:
pattern=s=outcome=repl=expected=None
if len(t)==5:
pattern, s, outcome, repl, expected = t
elif len(t)==3:
pattern, s, outcome = t
else:
raise ('Test tuples should have 3 or 5 fields',t)
try:
matobj=re.search(pattern, s)
except:
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
pass
else:
print('=== Unexpected exception:', matobj, pattern, s)
if outcome==FAIL:
if matobj==None: pass # No match, as expected
else: print('=== Succeeded incorrectly', obj, matobj, pattern, s)
elif outcome==SUCCEED:
if matobj!=None:
# Matched, as expected, so now we compute the
# result string and compare it to our expected result.
found=matobj.group(0)
repl = repl.replace("found", str(found))
for i in range(1,11):
if "g"+str(i) in repl:
gi = str(matobj.group(i))
repl = repl.replace("g"+str(i), gi)
if len(t) == 5:
repl = repl.replace('+', '')
repl = repl.replace('\"', '')
if repl!=expected:
print( '=== grouping error', t,
str(repl)+' should be '+str(expected))
RAISE()
else:
print ('=== Failed incorrectly', t)
def test_re_mod_match(verbose = None):
"""
some tests borrowed from cpython
testing re.match(), and matobj.group()
"""
regex_tests = testsuite.match_regex_tests
for t in regex_tests:
pattern=s=outcome=repl=expected=None
if len(t)==5:
pattern, s, outcome, repl, expected = t
elif len(t)==3:
pattern, s, outcome = t
else:
raise ('Test tuples should have 3 or 5 fields',t)
try:
matobj=re.match(pattern, s)
except:
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
pass
else:
print('=== Unexpected exception:', matobj, pattern, s)
if outcome==FAIL:
if matobj==None: pass # No match, as expected
else: print('=== Succeeded incorrectly', matobj, pattern, s)
elif outcome==SUCCEED:
if matobj!=None:
# Matched, as expected, so now we compute the
# result string and compare it to our expected result.
found=matobj.group(0)
repl = repl.replace("found", str(found))
for i in range(1,11):
if "g"+str(i) in repl:
gi = str(matobj.group(i))
repl = repl.replace("g"+str(i), gi)
if len(t) == 5:
repl = repl.replace('+', '')
repl = repl.replace('\"', '')
if repl!=expected:
print( '=== grouping error', t,
str(repl)+' should be '+str(expected))
RAISE()
else:
print ('=== Failed incorrectly', t)
def test_re_obj_split(verbose = None):
"""
test re.compile(), and reobj.split()
"""
regex_tests = testsuite.split_regex_tests
for t in regex_tests:
pattern, s, outcome, maxsplit, fields = t
try:
reobj = re.compile(pattern)
except:
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
pass
else:
print('=== Unexpected exception:', pattern, s,
outcome, maxsplit, fields)
try:
fldlst=reobj.split(s, maxsplit)
except:
if outcome == SYNTAX_ERROR:
continue
else:
print('=== Unexpected exception:', pattern, s,
outcome, maxsplit, fields)
if outcome==FAIL:
pass # No match, as expected
elif outcome==SUCCEED:
if fldlst:
# Matched, as expected, so now we compute the
# result string and compare it to our expected result.
if verbose:
fldstr = fieldstr = ""
for item in fldlst:
fldstr = fldstr + str(item) + " | "
for item in fields:
fieldstr = fieldstr + str(item) + " | "
print(fldstr, "~~~", fieldstr)
if len(fields) != len(fldlst):
print('=== Not coherent 1')
RAISE()
for i in range(len(fields)):
if fields[i] != fldlst[i]:
if verbose:
print('=== Not coherent 2', pattern, s,
outcome, maxsplit, fields, i,
fields[i],'(',len(fields[i]),')', ' | ',
fldlst[i],'(',len(fldlst[i]),')')
else:
print('=== Not coherent 2')
RAISE()
else:
print ('=== Failed incorrectly', pattern, s,
outcome, maxsplit, fields)
def test_re_mod_split(verbose = None):
"""
test re.split()
"""
regex_tests = testsuite.split_regex_tests
for t in regex_tests:
pattern, s, outcome, maxsplit, fields = t
try:
fldlst=re.split(pattern, s, maxsplit)
except:
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
continue
else:
print('=== Unexpected exception:', pattern, s,
outcome, maxsplit, fields)
if outcome==FAIL:
pass # No match, as expected
elif outcome==SUCCEED:
if fldlst:
# Matched, as expected, so now we compute the
# result string and compare it to our expected result.
if verbose:
fldstr = fieldstr = ""
for item in fldlst:
fldstr = fldstr + str(item) + " | "
for item in fields:
fieldstr = fieldstr + str(item) + " | "
print(fldstr, "~~~", fieldstr)
if len(fields) != len(fldlst):
print('=== Not coherent 1')
RAISE()
for i in range(len(fields)):
if fields[i] != fldlst[i]:
if verbose:
print('=== Not coherent 2', pattern, s,
outcome, maxsplit, fields, i,
fields[i],'(',len(fields[i]),')', ' | ',
fldlst[i],'(',len(fldlst[i]),')')
else:
print('=== Not coherent 2')
RAISE()
else:
print ('=== Failed incorrectly', pattern, s,
outcome, maxsplit, fields)
def test_re_obj_findall(verbose = None):
"""
test re.compile(), and reobj.findall()
"""
regex_tests = testsuite.findall_regex_tests
for t in regex_tests:
pattern, s, outcome, pos, fields = t
try:
reobj = re.compile(pattern)
except:
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
pass
else:
print('=== Unexpected exception:', pattern, s,
outcome, pos, fields)
try:
fldlst=reobj.findall(s, pos)
except:
if outcome == SYNTAX_ERROR:
continue
else:
print('=== Unexpected exception:', pattern, s,
outcome, pos, fields)
if outcome==FAIL:
pass # No match, as expected
elif outcome==SUCCEED:
if fldlst:
# Matched, as expected, so now we compute the
# result string and compare it to our expected result.
if verbose:
fldstr = fieldstr = ""
for item in fldlst:
fldstr = fldstr + str(item) + " | "
for item in fields:
fieldstr = fieldstr + str(item) + " | "
print(fldstr, "~~~", fieldstr)
if len(fields) != len(fldlst):
print('=== Not coherent 1')
RAISE()
for i in range(len(fields)):
if fields[i] != fldlst[i]:
if verbose:
print('=== Not coherent 2', pattern, s,
outcome, maxsplit, fields, i,
fields[i],'(',len(fields[i]),')', ' | ',
fldlst[i],'(',len(fldlst[i]),')')
else:
print('=== Not coherent 2')
RAISE()
else:
print ('=== Failed incorrectly', pattern, s,
outcome, pos, fields)
def test_re_mod_findall(verbose = None):
"""
test re.findall()
"""
regex_tests = testsuite.mod_findall_regex_tests
for t in regex_tests:
pattern, s, outcome, pos, fields = t # pos is not used
try:
fldlst=re.findall(pattern, s)
except:
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
continue
else:
print('=== Unexpected exception:', pattern, s,
outcome, pos, fields)
if outcome==FAIL:
pass # No match, as expected
elif outcome==SUCCEED:
if fldlst:
# Matched, as expected, so now we compute the
# result string and compare it to our expected result.
if verbose:
fldstr = fieldstr = ""
for item in fldlst:
fldstr = fldstr + str(item) + " | "
for item in fields:
fieldstr = fieldstr + str(item) + " | "
print(fldstr, "~~~", fieldstr)
if len(fields) != len(fldlst):
print('=== Not coherent 1')
RAISE()
for i in range(len(fields)):
if fields[i] != fldlst[i]:
if verbose:
print('=== Not coherent 2', pattern, s,
outcome, maxsplit, fields, i,
fields[i],'(',len(fields[i]),')', ' | ',
fldlst[i],'(',len(fldlst[i]),')')
else:
print('=== Not coherent 2')
RAISE()
else:
print ('=== Failed incorrectly', pattern, s,
outcome, pos, fields)
def test_mat_obj_groups(verbose = None):
"""
test re.search(), and matobj.groups()
'verbose' is for debugging, when 'verbose' is true, print extra info
"""
regex_tests = testsuite.matobj_groups_regex_tests
for t in regex_tests:
pattern, s, outcome, fields, grpidx, start, end = t
try:
matobj=re.search(pattern, s)
except:
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
continue
else:
print('=== Unexpected exception 1:', pattern, s,
outcome,fields)
try:
if outcome==SUCCEED: assert(matobj != None)
fldlst = matobj.groups()
except:
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
continue
else:
print('=== Unexpected exception 2:', pattern, s,
outcome,fields)
if outcome==FAIL:
pass # No match, as expected
elif outcome==SUCCEED:
if fldlst and fields:
# Matched, as expected, so now we compute the
# result string and compare it to our expected result.
if verbose:
fldstr = fieldstr = ""
for item in fldlst:
fldstr = fldstr + str(item) + " | "
for item in fields:
fieldstr = fieldstr + str(item) + " | "
print(fldstr, "~~~", fieldstr)
if len(fields) != len(fldlst):
print('=== Not coherent 2')
RAISE()
for i in range(len(fields)):
if fields[i] != fldlst[i]:
if verbose:
print('=== Not coherent', pattern, s,
outcome,fields, i,
fields[i],'(',len(fields[i]),')', ' | ',
fldlst[i],'(',len(fldlst[i]),')')
else:
print('=== Not coherent')
RAISE()
elif not len(fldlst) and not len(fields):
# output is empty, as expected
if verbose:
print("output is empty, as expected")
continue
else:
if verbose:
for item in fldlst:
print(item,)
print()
for item in fields:
print(item,)
print()
print ('=== Failed incorrectly', pattern, s,
outcome,fields,fldlst)
def test_mat_obj_start(verbose = None):
"""
test re.search(), and matobj.start()
'verbose' is for debugging, when 'verbose' is true, print extra info
"""
regex_tests = testsuite.matobj_groups_regex_tests
for t in regex_tests:
pattern, s, outcome, fields, grpidx, start, end = t
try:
matobj=re.search(pattern, s)
except:
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
continue
else:
print('=== Unexpected exception 1:', pattern, s,
outcome,fields)
try:
if outcome==SUCCEED: assert(matobj != None)
fldlst = matobj.groups()
except:
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
continue
else:
print('=== Unexpected exception 2:', pattern, s,
outcome,fields)
if outcome==FAIL:
pass # No match, as expected
elif outcome==SUCCEED:
if grpidx > 0:
if matobj.start(grpidx) == start:
pass
else:
if verbose:
print ('=== Failed incorrectly', pattern, s,
outcome,fields,fldlst)
raise("testing failed")
def test_mat_obj_end(verbose = None):
"""
test re.search(), and matobj.end()
'verbose' is for debugging, when 'verbose' is true, print extra info
"""
regex_tests = testsuite.matobj_groups_regex_tests
for t in regex_tests:
pattern, s, outcome, fields, grpidx, start, end = t
try:
matobj=re.search(pattern, s)
except:
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
continue
else:
print('=== Unexpected exception 1:', pattern, s,
outcome,fields)
try:
if outcome==SUCCEED: assert(matobj != None)
fldlst = matobj.groups()
except:
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
continue
else:
print('=== Unexpected exception 2:', pattern, s,
outcome,fields)
if outcome==FAIL:
pass # No match, as expected
elif outcome==SUCCEED:
if grpidx > 0:
if matobj.end(grpidx) == end:
pass
else:
if verbose:
print ('=== Failed incorrectly', pattern, s,
outcome,fields,fldlst, matobj.end(grpidx), end)
raise("testing failed")
def test_mat_obj_span(verbose = None):
"""
test re.search(), and matobj.span()
'verbose' is for debugging, when 'verbose' is true, print extra info
"""
regex_tests = testsuite.matobj_groups_regex_tests
for t in regex_tests:
pattern, s, outcome, fields, grpidx, start, end = t
try:
matobj=re.search(pattern, s)
except:
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
continue
else:
print('=== Unexpected exception 1:', pattern, s,
outcome,fields)
try:
if outcome==SUCCEED: assert(matobj != None)
fldlst = matobj.groups()
except:
if outcome==SYNTAX_ERROR:
# This should have been a syntax error; forget it.
continue
else:
print('=== Unexpected exception 2:', pattern, s,
outcome,fields)
if outcome==FAIL:
pass # No match, as expected
elif outcome==SUCCEED:
if (grpidx > 0):
spstart, spend = matobj.span(grpidx)
if spstart == start and spend == end:
pass
else:
if verbose:
print ('=== Failed incorrectly', pattern, s,
outcome,fields,fldlst)
raise("testing failed")
if __name__ == "__main__":
main()

367
programs/develop/tinypy/modules/re/testsuite.py Normal file
View File

@@ -0,0 +1,367 @@
# Test suite (for verifying correctness)
#
# The test suite is a list of 5- or 3-tuples. The 5 parts of a
# complete tuple are:
# element 0: a string containing the pattern
# 1: the string to match against the pattern
# 2: the expected result (0 - SUCCEED, 1 - FAIL, 2 - SYNTAX_ERROR)
# 3: a string that will be eval()'ed to produce a test string.
# This is an arbitrary Python expression; the available
# variables are "found" (the whole match), and "g1", "g2", ...
# up to "g10" contain the contents of each group, or the
# string 'None' if the group wasn't given a value.
# 4: The expected result of evaluating the expression.
# If the two don't match, an error is reported.
#
# If the regex isn't expected to work, the latter two elements can be omitted.
# test suite for search
search_regex_tests=[
['abc', 'abc', 0, 'found', 'abc'],
['abc', 'xbc', 1],
['abc', 'axc', 1],
['abc', 'abx', 1],
['abc', 'xabcy', 0, 'found', 'abc'],
['abc', 'ababc', 0, 'found', 'abc'],
['ab*c', 'abc', 0, 'found', 'abc'],
['ab*bc', 'abc', 0, 'found', 'abc'],
['ab*bc', 'abbc', 0, 'found', 'abbc'],
['ab*bc', 'abbbbc', 0, 'found', 'abbbbc'],
['ab+bc', 'abbc', 0, 'found', 'abbc'],
['ab+bc', 'abc', 1],
['ab+bc', 'abq', 1],
['ab+bc', 'abbbbc', 0, 'found', 'abbbbc'],
['ab?bc', 'abbc', 0, 'found', 'abbc'],
['ab?bc', 'abc', 0, 'found', 'abc'],
['ab?bc', 'abbbbc', 1],
['ab?c', 'abc', 0, 'found', 'abc'],
['^abc$', 'abc', 0, 'found', 'abc'],
['^abc$', 'abcc', 1],
['^abc', 'abcc', 0, 'found', 'abc'],
['^abc$', 'aabc', 1],
['abc$', 'aabc', 0, 'found', 'abc'],
['^', 'abc', 0, 'found+"-"', '-'],
['$', 'abc', 0, 'found+"-"', '-'],
['a.c', 'abc', 0, 'found', 'abc'],
['a.c', 'axc', 0, 'found', 'axc'],
['a.*c', 'axyzc', 0, 'found', 'axyzc'],
['a.*c', 'axyzd', 1],
['a[bc]d', 'abc', 1],
['a[bc]d', 'abd', 0, 'found', 'abd'],
['a[b-d]e', 'abd', 1],
['a[b-d]e', 'ace', 0, 'found', 'ace'],
['a[b-d]', 'aac', 0, 'found', 'ac'],
['a[-b]', 'a-', 0, 'found', 'a-'],
['a[b-]', 'a-', 0, 'found', 'a-'],
['a[]b', '-', 2],
['a[', '-', 2],
['a\\', '-', 2],
['abc\\)', '-', 2],
['\\(abc', '-', 2],
['a]', 'a]', 0, 'found', 'a]'],
['a[]]b', 'a]b', 0, 'found', 'a]b'],
['a[^bc]d', 'aed', 0, 'found', 'aed'],
['a[^bc]d', 'abd', 1],
['a[^-b]c', 'adc', 0, 'found', 'adc'],
['a[^-b]c', 'a-c', 1],
['a[^]b]c', 'a]c', 1],
['a[^]b]c', 'adc', 0, 'found', 'adc'],
['\\ba\\b', 'a-', 0, '"-"', '-'],
['\\ba\\b', '-a', 0, '"-"', '-'],
['\\ba\\b', '-a-', 0, '"-"', '-'],
['\\by\\b', 'xy', 1],
['\\by\\b', 'yz', 1],
['\\by\\b', 'xyz', 1],
['ab\\|cd', 'abc', 0, 'found', 'ab'],
['ab\\|cd', 'abcd', 0, 'found', 'ab'],
['\\(\\)ef', 'def', 0, 'found+"-"+g1', 'ef-'],
['$b', 'b', 1],
['a(b', 'a(b', 0, 'found+"-"+g1', 'a(b-None'],
['a(*b', 'ab', 0, 'found', 'ab'],
['a(*b', 'a((b', 0, 'found', 'a((b'],
['a\\\\b', 'a\\b', 0, 'found', 'a\\b'],
['\\(\\(a\\)\\)', 'abc', 0, 'found+"-"+g1+"-"+g2', 'a-a-a'],
['\\(a\\)b\\(c\\)', 'abc', 0, 'found+"-"+g1+"-"+g2', 'abc-a-c'],
['a+b+c', 'aabbabc', 0, 'found', 'abc'],
['\\(a+\\|b\\)*', 'ab', 0, 'found+"-"+g1', 'ab-b'],
['\\(a+\\|b\\)+', 'ab', 0, 'found+"-"+g1', 'ab-b'],
['\\(a+\\|b\\)?', 'ab', 0, 'found+"-"+g1', 'a-a'],
['\\)\\(', '-', 2],
['[^ab]*', 'cde', 0, 'found', 'cde'],
['abc', '', 1],
['a*', '', 0, 'found', ''],
['a\\|b\\|c\\|d\\|e', 'e', 0, 'found', 'e'],
['\\(a\\|b\\|c\\|d\\|e\\)f', 'ef', 0, 'found+"-"+g1', 'ef-e'],
['abcd*efg', 'abcdefg', 0, 'found', 'abcdefg'],
['ab*', 'xabyabbbz', 0, 'found', 'ab'],
['ab*', 'xayabbbz', 0, 'found', 'a'],
['\\(ab\\|cd\\)e', 'abcde', 0, 'found+"-"+g1', 'cde-cd'],
['[abhgefdc]ij', 'hij', 0, 'found', 'hij'],
['^\\(ab\\|cd\\)e', 'abcde', 1, 'xg1y', 'xy'],
['\\(abc\\|\\)ef', 'abcdef', 0, 'found+"-"+g1', 'ef-'],
['\\(a\\|b\\)c*d', 'abcd', 0, 'found+"-"+g1', 'bcd-b'],
['\\(ab\\|ab*\\)bc', 'abc', 0, 'found+"-"+g1', 'abc-a'],
['a\\([bc]*\\)c*', 'abc', 0, 'found+"-"+g1', 'abc-bc'],
['a\\([bc]*\\)\\(c*d\\)', 'abcd', 0, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'],
['a\\([bc]+\\)\\(c*d\\)', 'abcd', 0, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'],
['a\\([bc]*\\)\\(c+d\\)', 'abcd', 0, 'found+"-"+g1+"-"+g2', 'abcd-b-cd'],
['a[bcd]*dcdcde', 'adcdcde', 0, 'found', 'adcdcde'],
['a[bcd]+dcdcde', 'adcdcde', 1],
['\\(ab\\|a\\)b*c', 'abc', 0, 'found+"-"+g1', 'abc-ab'],
['\\(\\(a\\)\\(b\\)c\\)\\(d\\)', 'abcd', 0, 'g1+"-"+g2+"-"+g3+"-"+g4', 'abc-a-b-d'],
['[a-zA-Z_][a-zA-Z0-9_]*', 'alpha', 0, 'found', 'alpha'],
['^a\\(bc+\\|b[eh]\\)g\\|.h$', 'abh', 0, 'found+"-"+g1', 'bh-None'],
['\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'effgz', 0, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'],
['\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'ij', 0, 'found+"-"+g1+"-"+g2', 'ij-ij-j'],
['\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'effg', 1],
['\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'bcdd', 1],
['\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'reffgz', 0, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'],
['\\(\\(\\(\\(\\(\\(\\(\\(\\(a\\)\\)\\)\\)\\)\\)\\)\\)\\)', 'a', 0, 'found', 'a'],
['multiple words of text', 'uh-uh', 1],
['multiple words', 'multiple words, yeah', 0, 'found', 'multiple words'],
['\\(.*\\)c\\(.*\\)', 'abcde', 0, 'found+"-"+g1+"-"+g2', 'abcde-ab-de'],
['(\\(.*\\), \\(.*\\))', '(a, b)', 0, 'g2+"-"+g1', 'b-a'],
['[k]', 'ab', 1],
['a[-]?c', 'ac', 0, 'found', 'ac'],
['\\(abc\\)\\1', 'abcabc', 0, 'g1', 'abc'],
['\\([a-c]*\\)\\1', 'abcabc', 0, 'g1', 'abc'],
['^\\(.+\\)?B', 'AB', 0, 'g1', 'A'],
['\\(a+\\).\\1$', 'aaaaa', 0, 'found+"-"+g1', 'aaaaa-aa'],
['^\\(a+\\).\\1$', 'aaaa', 1],
['\\(abc\\)\\1', 'abcabc', 0, 'found+"-"+g1', 'abcabc-abc'],
['\\([a-c]+\\)\\1', 'abcabc', 0, 'found+"-"+g1', 'abcabc-abc'],
['\\(a\\)\\1', 'aa', 0, 'found+"-"+g1', 'aa-a'],
['\\(a+\\)\\1', 'aa', 0, 'found+"-"+g1', 'aa-a'],
['\\(a+\\)+\\1', 'aa', 0, 'found+"-"+g1', 'aa-a'],
['\\(a\\).+\\1', 'aba', 0, 'found+"-"+g1', 'aba-a'],
['\\(a\\)ba*\\1', 'aba', 0, 'found+"-"+g1', 'aba-a'],
['\\(aa\\|a\\)a\\1$', 'aaa', 0, 'found+"-"+g1', 'aaa-a'],
['\\(a\\|aa\\)a\\1$', 'aaa', 0, 'found+"-"+g1', 'aaa-a'],
['\\(a+\\)a\\1$', 'aaa', 0, 'found+"-"+g1', 'aaa-a'],
['\\([abc]*\\)\\1', 'abcabc', 0, 'found+"-"+g1', 'abcabc-abc'],
['\\(a\\)\\(b\\)c\\|ab', 'ab', 0, 'found+"-"+g1+"-"+g2', 'ab-None-None'],
['\\(a\\)+x', 'aaax', 0, 'found+"-"+g1', 'aaax-a'],
['\\([ac]\\)+x', 'aacx', 0, 'found+"-"+g1', 'aacx-c'],
['\\([^/]*/\\)*sub1/', 'd:msgs/tdir/sub1/trial/away.cpp', 0, 'found+"-"+g1', 'd:msgs/tdir/sub1/-tdir/'],
['\\([^.]*\\)\\.\\([^:]*\\):[T ]+\\(.*\\)', 'track1.title:TBlah blah blah', 0, 'found+"-"+g1+"-"+g2+"-"+g3', 'track1.title:TBlah blah blah-track1-title-Blah blah blah'],
['\\([^N]*N\\)+', 'abNNxyzN', 0, 'found+"-"+g1', 'abNNxyzN-xyzN'],
['\\([^N]*N\\)+', 'abNNxyz', 0, 'found+"-"+g1', 'abNN-N'],
['\\([abc]*\\)x', 'abcx', 0, 'found+"-"+g1', 'abcx-abc'],
['\\([abc]*\\)x', 'abc', 1],
['\\([xyz]*\\)x', 'abcx', 0, 'found+"-"+g1', 'x-'],
['\\(a\\)+b\\|aac', 'aac', 0, 'found+"-"+g1', 'aac-None'],
['\\<a', 'a', 0, 'found', 'a'],
['\\<a', '!', 1],
['a\\<b', 'ab', 1],
['a\\>', 'ab', 1],
['a\\>', 'a!', 0, 'found', 'a'],
['a\\>', 'a', 0, 'found', 'a'],
]
# test suite for match
match_regex_tests=[
['abc', 'abc', 0, 'found', 'abc'],
['abc', 'xbc', 1],
['abc', 'axc', 1],
['abc', 'abx', 1],
['abc', 'xabcy', 1],
['abc', 'ababc', 1],
['ab*c', 'abc', 0, 'found', 'abc'],
['ab*bc', 'abc', 0, 'found', 'abc'],
['ab*bc', 'abbc', 0, 'found', 'abbc'],
['ab*bc', 'abbbbc', 0, 'found', 'abbbbc'],
['ab+bc', 'abbc', 0, 'found', 'abbc'],
['ab+bc', 'abc', 1],
['ab+bc', 'abq', 1],
['ab+bc', 'abbbbc', 0, 'found', 'abbbbc'],
['ab?bc', 'abbc', 0, 'found', 'abbc'],
['ab?bc', 'abc', 0, 'found', 'abc'],
['ab?bc', 'abbbbc', 1],
['ab?c', 'abc', 0, 'found', 'abc'],
['^abc$', 'abc', 0, 'found', 'abc'],
['^abc$', 'abcc', 1],
['^abc', 'abcc', 0, 'found', 'abc'],
['^abc$', 'aabc', 1],
['abc$', 'aabc', 1],
['^', 'abc', 0, 'found+"-"', '-'],
['$', 'abc', 1],
['a.c', 'abc', 0, 'found', 'abc'],
['a.c', 'axc', 0, 'found', 'axc'],
['a.*c', 'axyzc', 0, 'found', 'axyzc'],
['a.*c', 'axyzd', 1],
['a[bc]d', 'abc', 1],
['a[bc]d', 'abd', 0, 'found', 'abd'],
['a[b-d]e', 'abd', 1],
['a[b-d]e', 'ace', 0, 'found', 'ace'],
['a[b-d]', 'aac', 1],
['a[-b]', 'a-', 0, 'found', 'a-'],
['a[b-]', 'a-', 0, 'found', 'a-'],
['a[]b', '-', 2],
['a[', '-', 2],
['a\\', '-', 2],
['abc\\)', '-', 2],
['\\(abc', '-', 2],
['a]', 'a]', 0, 'found', 'a]'],
['a[]]b', 'a]b', 0, 'found', 'a]b'],
['a[^bc]d', 'aed', 0, 'found', 'aed'],
['a[^bc]d', 'abd', 1],
['a[^-b]c', 'adc', 0, 'found', 'adc'],
['a[^-b]c', 'a-c', 1],
['a[^]b]c', 'a]c', 1],
['a[^]b]c', 'adc', 0, 'found', 'adc'],
['\\ba\\b', 'a-', 0, '"-"', '-'],
['\\ba\\b', '-a', 1],
['\\ba\\b', '-a-', 1],
['\\by\\b', 'xy', 1],
['\\by\\b', 'yz', 1],
['\\by\\b', 'xyz', 1],
['ab\\|cd', 'abc', 0, 'found', 'ab'],
['ab\\|cd', 'abcd', 0, 'found', 'ab'],
['\\(\\)ef', 'def', 1],
['$b', 'b', 1],
['a(b', 'a(b', 0, 'found+"-"+g1', 'a(b-None'],
['a(*b', 'ab', 0, 'found', 'ab'],
['a(*b', 'a((b', 0, 'found', 'a((b'],
['a\\\\b', 'a\\b', 0, 'found', 'a\\b'],
['\\(\\(a\\)\\)', 'abc', 0, 'found+"-"+g1+"-"+g2', 'a-a-a'],
['\\(a\\)b\\(c\\)', 'abc', 0, 'found+"-"+g1+"-"+g2', 'abc-a-c'],
['a+b+c', 'aabbabc', 1],
['\\(a+\\|b\\)*', 'ab', 0, 'found+"-"+g1', 'ab-b'],
['\\(a+\\|b\\)+', 'ab', 0, 'found+"-"+g1', 'ab-b'],
['\\(a+\\|b\\)?', 'ab', 0, 'found+"-"+g1', 'a-a'],
['\\)\\(', '-', 2],
['[^ab]*', 'cde', 0, 'found', 'cde'],
['abc', '', 1],
['a*', '', 0, 'found', ''],
['a\\|b\\|c\\|d\\|e', 'e', 0, 'found', 'e'],
['\\(a\\|b\\|c\\|d\\|e\\)f', 'ef', 0, 'found+"-"+g1', 'ef-e'],
['abcd*efg', 'abcdefg', 0, 'found', 'abcdefg'],
['ab*', 'xabyabbbz', 1],
['ab*', 'xayabbbz', 1],
['\\(ab\\|cd\\)e', 'abcde', 1],
['[abhgefdc]ij', 'hij', 0, 'found', 'hij'],
['^\\(ab\\|cd\\)e', 'abcde', 1, 'xg1y', 'xy'],
['\\(abc\\|\\)ef', 'abcdef', 1],
['\\(a\\|b\\)c*d', 'abcd', 1],
['\\(ab\\|ab*\\)bc', 'abc', 0, 'found+"-"+g1', 'abc-a'],
['a\\([bc]*\\)c*', 'abc', 0, 'found+"-"+g1', 'abc-bc'],
['a\\([bc]*\\)\\(c*d\\)', 'abcd', 0, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'],
['a\\([bc]+\\)\\(c*d\\)', 'abcd', 0, 'found+"-"+g1+"-"+g2', 'abcd-bc-d'],
['a\\([bc]*\\)\\(c+d\\)', 'abcd', 0, 'found+"-"+g1+"-"+g2', 'abcd-b-cd'],
['a[bcd]*dcdcde', 'adcdcde', 0, 'found', 'adcdcde'],
['a[bcd]+dcdcde', 'adcdcde', 1],
['\\(ab\\|a\\)b*c', 'abc', 0, 'found+"-"+g1', 'abc-ab'],
['\\(\\(a\\)\\(b\\)c\\)\\(d\\)', 'abcd', 0, 'g1+"-"+g2+"-"+g3+"-"+g4', 'abc-a-b-d'],
['[a-zA-Z_][a-zA-Z0-9_]*', 'alpha', 0, 'found', 'alpha'],
['^a\\(bc+\\|b[eh]\\)g\\|.h$', 'abh', 1],
['\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'effgz', 0, 'found+"-"+g1+"-"+g2', 'effgz-effgz-None'],
['\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'ij', 0, 'found+"-"+g1+"-"+g2', 'ij-ij-j'],
['\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'effg', 1],
['\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'bcdd', 1],
['\\(bc+d$\\|ef*g.\\|h?i\\(j\\|k\\)\\)', 'reffgz', 1],
['\\(\\(\\(\\(\\(\\(\\(\\(\\(a\\)\\)\\)\\)\\)\\)\\)\\)\\)', 'a', 0, 'found', 'a'],
['multiple words of text', 'uh-uh', 1],
['multiple words', 'multiple words, yeah', 0, 'found', 'multiple words'],
['\\(.*\\)c\\(.*\\)', 'abcde', 0, 'found+"-"+g1+"-"+g2', 'abcde-ab-de'],
['(\\(.*\\), \\(.*\\))', '(a, b)', 0, 'g2+"-"+g1', 'b-a'],
['[k]', 'ab', 1],
['a[-]?c', 'ac', 0, 'found', 'ac'],
['\\(abc\\)\\1', 'abcabc', 0, 'g1', 'abc'],
['\\([a-c]*\\)\\1', 'abcabc', 0, 'g1', 'abc'],
['^\\(.+\\)?B', 'AB', 0, 'g1', 'A'],
['\\(a+\\).\\1$', 'aaaaa', 0, 'found+"-"+g1', 'aaaaa-aa'],
['^\\(a+\\).\\1$', 'aaaa', 1],
['\\(abc\\)\\1', 'abcabc', 0, 'found+"-"+g1', 'abcabc-abc'],
['\\([a-c]+\\)\\1', 'abcabc', 0, 'found+"-"+g1', 'abcabc-abc'],
['\\(a\\)\\1', 'aa', 0, 'found+"-"+g1', 'aa-a'],
['\\(a+\\)\\1', 'aa', 0, 'found+"-"+g1', 'aa-a'],
['\\(a+\\)+\\1', 'aa', 0, 'found+"-"+g1', 'aa-a'],
['\\(a\\).+\\1', 'aba', 0, 'found+"-"+g1', 'aba-a'],
['\\(a\\)ba*\\1', 'aba', 0, 'found+"-"+g1', 'aba-a'],
['\\(aa\\|a\\)a\\1$', 'aaa', 0, 'found+"-"+g1', 'aaa-a'],
['\\(a\\|aa\\)a\\1$', 'aaa', 0, 'found+"-"+g1', 'aaa-a'],
['\\(a+\\)a\\1$', 'aaa', 0, 'found+"-"+g1', 'aaa-a'],
['\\([abc]*\\)\\1', 'abcabc', 0, 'found+"-"+g1', 'abcabc-abc'],
['\\(a\\)\\(b\\)c\\|ab', 'ab', 0, 'found+"-"+g1+"-"+g2', 'ab-None-None'],
['\\(a\\)+x', 'aaax', 0, 'found+"-"+g1', 'aaax-a'],
['\\([ac]\\)+x', 'aacx', 0, 'found+"-"+g1', 'aacx-c'],
['\\([^/]*/\\)*sub1/', 'd:msgs/tdir/sub1/trial/away.cpp', 0, 'found+"-"+g1', 'd:msgs/tdir/sub1/-tdir/'],
['\\([^.]*\\)\\.\\([^:]*\\):[T ]+\\(.*\\)', 'track1.title:TBlah blah blah', 0, 'found+"-"+g1+"-"+g2+"-"+g3', 'track1.title:TBlah blah blah-track1-title-Blah blah blah'],
['\\([^N]*N\\)+', 'abNNxyzN', 0, 'found+"-"+g1', 'abNNxyzN-xyzN'],
['\\([^N]*N\\)+', 'abNNxyz', 0, 'found+"-"+g1', 'abNN-N'],
['\\([abc]*\\)x', 'abcx', 0, 'found+"-"+g1', 'abcx-abc'],
['\\([abc]*\\)x', 'abc', 1],
['\\([xyz]*\\)x', 'abcx', 1],
['\\(a\\)+b\\|aac', 'aac', 0, 'found+"-"+g1', 'aac-None'],
['\\<a', 'a', 0, 'found', 'a'],
['\\<a', '!', 1],
['a\\<b', 'ab', 1],
['a\\>', 'ab', 1],
['a\\>', 'a!', 0, 'found', 'a'],
['a\\>', 'a', 0, 'found', 'a'],
]
# test suite for split()
# element 0: pattern
# 1: string to split
# 3: compile result
# 4: maxsplit
# 5: splitted fields list
split_regex_tests = [
["[ |,]", "with you, nothing, and me", 0, 0, ["with","you","nothing","and","me"]],
["[ |,]", "with you, nothing, and me", 0, 1, ["with", "you, nothing, and me"]],
["\\ ", "send email to apply", 0, 0, ["send", "email", "to", "apply"]],
["\\ ", "send email to apply", 0, 2, ["send", "email", "to apply"]],
["[+ | -]", "+86-028-83201034", 0, 0, ["86", "028", "83201034"]],
["[+ | -]", "+86-028-83201034", 0, 1, ["86", "028-83201034"]],
["[*|#]", "slide show", 0, 0, ["slide show"]],
["(", "whats ever", 0, 1, ["whats ever"]],
["@#!~$%^&*()<>\n", "who knows", 0, 1, ["who knows"]],
]
# test suite for findall()
# element 0: pattern
# 1: string to match
# 3: compile result
# 4: starting position
# 5: grouped fields list
# reobj.find()
findall_regex_tests = [
["\\ ", "send email to apply", 0, 0, [" ", " ", " "]],
["\\ ", "send email to apply", 0, 5, [" ", " "]],
["[+ | -]", "+86-028-83201034", 0, 0, ["+", "-", "-"]],
["[+ | -]", "+86-028-83201034", 0, 1, ["-", "-"]],
["sl.*e\\|#", "slide show at Room #3", 0, 0, ["slide", "#"]],
["w.+s\\|e.*r", "whats ever", 0, 0, ["whats", "ever"]],
["Euler\\|Gauss", "Both Euler and Gauss are great mathematicians", 0, 0, ["Euler", "Gauss"]],
]
# module re.findall()
mod_findall_regex_tests = [
["\\ ", "send email to apply", 0, 0, [" ", " ", " "]],
["\\ ", "send email to apply", 0, 0, [" ", " ", " "]],
["[+ | -]", "+86-028-83201034", 0, 0, ["+", "-", "-"]],
["[+ | -]", "+86-028-83201034", 0, 0, ["+", "-", "-"]],
["sl.*e\\|#", "slide show at Room #3", 0, 0, ["slide", "#"]],
["w.+s\\|e.*r", "whats ever", 0, 0, ["whats", "ever"]],
["Euler\\|Gauss", "Both Euler and Gauss are great mathematicians", 0, 0, ["Euler", "Gauss"]],
]
# test for match object's groups() method
# element 0: pattern
# 1: string
# 2: compile result
# 3: matched fields, for groups()
# 4: group index, valid when > 0, for start(), end(), and span()
# 5: pattern's starting index in string, for start() and span()
# 6: pattern's ending index in string, for end() and span
matobj_groups_regex_tests = [
["\\(abc\\(.*xyz\\)\\(.*31415926\\)\\)", "where is abc and flurry xyz, which is pi 31415926, derived from ms", 0, ["abc and flurry xyz, which is pi 31415926"," and flurry xyz",", which is pi 31415926"], 2, 12, 27],
["[a\\|b]\\(.+\\)shoe\\([t]+\\)d", "bbbshoetttdxrznmlkjp", 0, ["bb", "ttt"], 1, 1, 3],
["abcdef", "xyah2oewoyqe030uabcdefwhalsdewnkhgiohyczb", 0, [], -1, 0, 0],
]