2020-06-08 00:04:23 +03:00
|
|
|
/*
|
|
|
|
|
2020-12-06 00:24:08 +03:00
|
|
|
regex 0.9h
|
2020-06-08 00:04:23 +03:00
|
|
|
|
|
|
|
Copyright (c) 2019-2020 Dario Deledda. All rights reserved.
|
|
|
|
Use of this source code is governed by an MIT license
|
|
|
|
that can be found in the LICENSE file.
|
|
|
|
|
|
|
|
This file contains regex module
|
|
|
|
|
|
|
|
Know limitation:
|
|
|
|
- find is implemented in a trivial way
|
|
|
|
- not full compliant PCRE
|
|
|
|
- not compliant POSIX ERE
|
|
|
|
|
|
|
|
|
|
|
|
*/
|
2020-01-13 15:30:41 +03:00
|
|
|
module regex
|
2020-01-14 04:45:08 +03:00
|
|
|
import strings
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
pub const(
|
2020-12-06 00:24:08 +03:00
|
|
|
v_regex_version = "0.9h" // regex module version
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
max_code_len = 256 // default small base code len for the regex programs
|
|
|
|
max_quantifier = 1073741824 // default max repetitions allowed for the quantifiers = 2^30
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// spaces chars (here only westerns!!) TODO: manage all the spaces from unicode
|
2020-05-22 00:33:51 +03:00
|
|
|
spaces = [` `, `\t`, `\n`, `\r`, `\v`, `\f`]
|
2020-01-13 15:30:41 +03:00
|
|
|
// new line chars for now only '\n'
|
2020-12-03 21:33:53 +03:00
|
|
|
new_line_list = [`\n`, `\r`]
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// Results
|
2020-05-22 00:33:51 +03:00
|
|
|
no_match_found = -1
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// Errors
|
2020-05-22 00:33:51 +03:00
|
|
|
compile_ok = 0 // the regex string compiled, all ok
|
|
|
|
err_char_unknown = -2 // the char used is unknow to the system
|
|
|
|
err_undefined = -3 // the compiler symbol is undefined
|
|
|
|
err_internal_error = -4 // Bug in the regex system!!
|
|
|
|
err_cc_alloc_overflow = -5 // memory for char class full!!
|
|
|
|
err_syntax_error = -6 // syntax error in regex compiling
|
|
|
|
err_groups_overflow = -7 // max number of groups reached
|
|
|
|
err_groups_max_nested = -8 // max number of nested group reached
|
|
|
|
err_group_not_balanced = -9 // group not balanced
|
|
|
|
err_group_qm_notation = -10 // group invalid notation
|
2020-01-13 15:30:41 +03:00
|
|
|
)
|
|
|
|
|
|
|
|
const(
|
|
|
|
//*************************************
|
|
|
|
// regex program instructions
|
|
|
|
//*************************************
|
2020-12-03 21:33:53 +03:00
|
|
|
ist_simple_char = u32(0x7FFFFFFF) // single char instruction, 31 bit available to char
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// char class 11 0100 AA xxxxxxxx
|
|
|
|
// AA = 00 regular class
|
|
|
|
// AA = 01 Negated class ^ char
|
2020-05-22 00:33:51 +03:00
|
|
|
ist_char_class = 0xD1000000 // MASK
|
|
|
|
ist_char_class_pos = 0xD0000000 // char class normal [abc]
|
|
|
|
ist_char_class_neg = 0xD1000000 // char class negate [^abc]
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// dot char 10 0110 xx xxxxxxxx
|
2020-05-22 00:33:51 +03:00
|
|
|
ist_dot_char = 0x98000000 // match any char except \n
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// backslash chars 10 0100 xx xxxxxxxx
|
2020-05-22 00:33:51 +03:00
|
|
|
ist_bsls_char = 0x90000000 // backslash char
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// OR | 10 010Y xx xxxxxxxx
|
2020-05-22 00:33:51 +03:00
|
|
|
ist_or_branch = 0x91000000 // OR case
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// groups 10 010Y xx xxxxxxxx
|
2020-05-22 00:33:51 +03:00
|
|
|
ist_group_start = 0x92000000 // group start (
|
|
|
|
ist_group_end = 0x94000000 // group end )
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// control instructions
|
2020-05-22 00:33:51 +03:00
|
|
|
ist_prog_end = u32(0x88000000) //10 0010 xx xxxxxxxx
|
2020-01-13 15:30:41 +03:00
|
|
|
//*************************************
|
|
|
|
)
|
|
|
|
|
2020-06-08 00:04:23 +03:00
|
|
|
/*
|
|
|
|
|
|
|
|
General Utilities
|
|
|
|
|
|
|
|
*/
|
2020-01-13 15:30:41 +03:00
|
|
|
// utf8util_char_len calculate the length in bytes of a utf8 char
|
|
|
|
[inline]
|
|
|
|
fn utf8util_char_len(b byte) int {
|
|
|
|
return (( 0xe5000000 >> (( b >> 3 ) & 0x1e )) & 3 ) + 1
|
|
|
|
}
|
|
|
|
|
|
|
|
// get_char get a char from position i and return an u32 with the unicode code
|
|
|
|
[inline]
|
2020-01-16 02:39:33 +03:00
|
|
|
fn (re RE) get_char(in_txt string, i int) (u32,int) {
|
2020-07-22 20:28:53 +03:00
|
|
|
ini := unsafe {in_txt.str[i]}
|
2020-01-13 15:30:41 +03:00
|
|
|
// ascii 8 bit
|
2020-12-03 21:33:53 +03:00
|
|
|
if (re.flag & f_bin) !=0 || ini & 0x80 == 0 {
|
2020-07-22 20:28:53 +03:00
|
|
|
return u32(ini), 1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
// unicode char
|
2020-07-22 20:28:53 +03:00
|
|
|
char_len := utf8util_char_len(ini)
|
2020-01-13 15:30:41 +03:00
|
|
|
mut tmp := 0
|
|
|
|
mut ch := u32(0)
|
|
|
|
for tmp < char_len {
|
2020-12-03 21:33:53 +03:00
|
|
|
ch = (ch << 8) | unsafe {in_txt.str[i + tmp]}
|
2020-01-13 15:30:41 +03:00
|
|
|
tmp++
|
|
|
|
}
|
|
|
|
return ch,char_len
|
|
|
|
}
|
|
|
|
|
|
|
|
// get_charb get a char from position i and return an u32 with the unicode code
|
|
|
|
[inline]
|
2020-01-16 02:39:33 +03:00
|
|
|
fn (re RE) get_charb(in_txt byteptr, i int) (u32,int) {
|
2020-04-23 02:16:16 +03:00
|
|
|
// ascii 8 bit
|
2020-12-03 21:33:53 +03:00
|
|
|
if (re.flag & f_bin) !=0 || unsafe {in_txt[i]} & 0x80 == 0 {
|
2020-07-22 20:28:53 +03:00
|
|
|
return u32(unsafe {in_txt[i]}), 1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
// unicode char
|
2020-07-22 20:28:53 +03:00
|
|
|
char_len := utf8util_char_len(unsafe {in_txt[i]})
|
2020-01-13 15:30:41 +03:00
|
|
|
mut tmp := 0
|
|
|
|
mut ch := u32(0)
|
|
|
|
for tmp < char_len {
|
2020-12-03 21:33:53 +03:00
|
|
|
ch = (ch << 8) | unsafe {in_txt[i + tmp]}
|
2020-01-13 15:30:41 +03:00
|
|
|
tmp++
|
|
|
|
}
|
|
|
|
return ch,char_len
|
|
|
|
}
|
|
|
|
|
|
|
|
[inline]
|
|
|
|
fn is_alnum(in_char byte) bool {
|
|
|
|
mut tmp := in_char - `A`
|
2020-12-03 21:33:53 +03:00
|
|
|
if tmp <= 25 { return true }
|
2020-01-13 15:30:41 +03:00
|
|
|
tmp = in_char - `a`
|
2020-12-03 21:33:53 +03:00
|
|
|
if tmp <= 25 { return true }
|
2020-01-13 15:30:41 +03:00
|
|
|
tmp = in_char - `0`
|
2020-12-03 21:33:53 +03:00
|
|
|
if tmp <= 9 { return true }
|
2020-01-28 22:34:11 +03:00
|
|
|
if tmp == `_` { return true }
|
2020-01-13 15:30:41 +03:00
|
|
|
return false
|
|
|
|
}
|
|
|
|
|
|
|
|
[inline]
|
|
|
|
fn is_not_alnum(in_char byte) bool {
|
|
|
|
return !is_alnum(in_char)
|
|
|
|
}
|
|
|
|
|
|
|
|
[inline]
|
|
|
|
fn is_space(in_char byte) bool {
|
2020-05-22 00:33:51 +03:00
|
|
|
return in_char in spaces
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
[inline]
|
|
|
|
fn is_not_space(in_char byte) bool {
|
|
|
|
return !is_space(in_char)
|
|
|
|
}
|
|
|
|
|
|
|
|
[inline]
|
|
|
|
fn is_digit(in_char byte) bool {
|
|
|
|
tmp := in_char - `0`
|
2020-12-03 21:33:53 +03:00
|
|
|
return tmp <= 0x09
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
[inline]
|
|
|
|
fn is_not_digit(in_char byte) bool {
|
|
|
|
return !is_digit(in_char)
|
|
|
|
}
|
|
|
|
|
|
|
|
[inline]
|
|
|
|
fn is_wordchar(in_char byte) bool {
|
|
|
|
return is_alnum(in_char) || in_char == `_`
|
|
|
|
}
|
|
|
|
|
|
|
|
[inline]
|
|
|
|
fn is_not_wordchar(in_char byte) bool {
|
|
|
|
return !is_alnum(in_char)
|
|
|
|
}
|
|
|
|
|
|
|
|
[inline]
|
|
|
|
fn is_lower(in_char byte) bool {
|
|
|
|
tmp := in_char - `a`
|
2020-12-03 21:33:53 +03:00
|
|
|
return tmp <= 25
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
[inline]
|
|
|
|
fn is_upper(in_char byte) bool {
|
|
|
|
tmp := in_char - `A`
|
2020-12-03 21:33:53 +03:00
|
|
|
return tmp <= 25
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
pub fn (re RE) get_parse_error_string(err int) string {
|
|
|
|
match err {
|
2020-05-22 00:33:51 +03:00
|
|
|
compile_ok { return "compile_ok" }
|
|
|
|
no_match_found { return "no_match_found" }
|
|
|
|
err_char_unknown { return "err_char_unknown" }
|
|
|
|
err_undefined { return "err_undefined" }
|
|
|
|
err_internal_error { return "err_internal_error" }
|
|
|
|
err_cc_alloc_overflow { return "err_cc_alloc_overflow" }
|
|
|
|
err_syntax_error { return "err_syntax_error" }
|
|
|
|
err_groups_overflow { return "err_groups_overflow" }
|
|
|
|
err_groups_max_nested { return "err_groups_max_nested" }
|
|
|
|
err_group_not_balanced { return "err_group_not_balanced" }
|
|
|
|
err_group_qm_notation { return "err_group_qm_notation" }
|
|
|
|
else { return "err_unknown" }
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-01-14 04:45:08 +03:00
|
|
|
// utf8_str convert and utf8 sequence to a printable string
|
|
|
|
[inline]
|
2020-08-27 07:46:18 +03:00
|
|
|
fn utf8_str(ch rune) string {
|
2020-01-14 04:45:08 +03:00
|
|
|
mut i := 4
|
|
|
|
mut res := ""
|
|
|
|
for i > 0 {
|
2020-12-03 21:33:53 +03:00
|
|
|
v := byte((ch >> ((i - 1) * 8)) & 0xFF)
|
2020-01-14 04:45:08 +03:00
|
|
|
if v != 0{
|
|
|
|
res += "${v:1c}"
|
|
|
|
}
|
|
|
|
i--
|
|
|
|
}
|
|
|
|
return res
|
|
|
|
}
|
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// simple_log default log function
|
|
|
|
fn simple_log(txt string) {
|
2020-01-16 02:39:33 +03:00
|
|
|
print(txt)
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
/******************************************************************************
|
|
|
|
*
|
|
|
|
* Token Structs
|
|
|
|
*
|
|
|
|
******************************************************************************/
|
2020-09-25 13:02:32 +03:00
|
|
|
pub type FnValidator = fn (byte) bool
|
2020-01-13 15:30:41 +03:00
|
|
|
struct Token{
|
|
|
|
mut:
|
2020-08-27 07:46:18 +03:00
|
|
|
ist rune
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-01-16 02:39:33 +03:00
|
|
|
// char
|
2020-12-03 21:33:53 +03:00
|
|
|
ch rune // char of the token if any
|
|
|
|
ch_len byte // char len
|
2020-01-16 02:39:33 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// Quantifiers / branch
|
2020-08-27 07:46:18 +03:00
|
|
|
rep_min int // used also for jump next in the OR branch [no match] pc jump
|
|
|
|
rep_max int // used also for jump next in the OR branch [ match] pc jump
|
2020-12-03 21:33:53 +03:00
|
|
|
greedy bool // greedy quantifier flag
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// Char class
|
2020-12-03 21:33:53 +03:00
|
|
|
cc_index int = -1
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// counters for quantifier check (repetitions)
|
2020-08-27 07:46:18 +03:00
|
|
|
rep int
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-01-18 09:38:00 +03:00
|
|
|
// validator function pointer
|
2020-12-03 21:33:53 +03:00
|
|
|
validator FnValidator
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// groups variables
|
2020-12-03 21:33:53 +03:00
|
|
|
group_rep int // repetition of the group
|
|
|
|
group_id int = -1 // id of the group
|
|
|
|
goto_pc int = -1 // jump to this PC if is needed
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-04-23 02:16:16 +03:00
|
|
|
// OR flag for the token
|
2020-12-03 21:33:53 +03:00
|
|
|
next_is_or bool // true if the next token is an OR
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-01-31 04:29:54 +03:00
|
|
|
[inline]
|
2020-05-17 14:51:18 +03:00
|
|
|
fn (mut tok Token) reset() {
|
2020-01-13 15:30:41 +03:00
|
|
|
tok.rep = 0
|
|
|
|
}
|
|
|
|
|
2020-06-08 00:04:23 +03:00
|
|
|
/*
|
|
|
|
|
|
|
|
Regex struct
|
|
|
|
|
|
|
|
*/
|
2020-01-13 15:30:41 +03:00
|
|
|
pub const (
|
2020-05-22 00:33:51 +03:00
|
|
|
f_nl = 0x00000001 // end the match when find a new line symbol
|
|
|
|
f_ms = 0x00000002 // match true only if the match is at the start of the string
|
|
|
|
f_me = 0x00000004 // match true only if the match is at the end of the string
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
f_efm = 0x00000100 // exit on first token matched, used by search
|
|
|
|
f_bin = 0x00000200 // work only on bytes, ignore utf-8
|
2020-01-28 22:34:11 +03:00
|
|
|
|
|
|
|
// behaviour modifier flags
|
2020-05-22 00:33:51 +03:00
|
|
|
//f_or = 0x00010000 // the OR work with concatenation like PCRE
|
|
|
|
f_src = 0x00020000 // search mode enabled
|
2020-01-13 15:30:41 +03:00
|
|
|
)
|
|
|
|
|
|
|
|
struct StateDotObj{
|
|
|
|
mut:
|
2020-01-18 09:38:00 +03:00
|
|
|
i int = -1 // char index in the input buffer
|
2020-01-25 21:12:23 +03:00
|
|
|
pc int = -1 // program counter saved
|
|
|
|
mi int = -1 // match_index saved
|
|
|
|
group_stack_index int = -1 // continuous save on capturing groups
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-09-25 13:02:32 +03:00
|
|
|
pub type FnLog = fn (string)
|
2020-04-25 23:42:48 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
pub
|
|
|
|
struct RE {
|
|
|
|
pub mut:
|
|
|
|
prog []Token
|
|
|
|
|
|
|
|
// char classes storage
|
|
|
|
cc []CharClass // char class list
|
2020-09-09 15:14:44 +03:00
|
|
|
cc_index int // index
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// state index
|
|
|
|
state_stack_index int= -1
|
|
|
|
state_stack []StateDotObj
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// groups
|
2020-12-03 21:33:53 +03:00
|
|
|
group_count int // number of groups in this regex struct
|
|
|
|
groups []int // groups index results
|
|
|
|
group_max_nested int = 3 // max nested group
|
|
|
|
group_max int = 8 // max allowed number of different groups
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-12-03 21:33:53 +03:00
|
|
|
group_csave []int = []int{} // groups continuous save array
|
|
|
|
group_csave_index int = -1 // groups continuous save index
|
2020-01-25 21:12:23 +03:00
|
|
|
|
2020-12-03 21:33:53 +03:00
|
|
|
group_map map[string]int // groups names map
|
2020-01-28 22:34:11 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// flags
|
2020-12-03 21:33:53 +03:00
|
|
|
flag int // flag for optional parameters
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// Debug/log
|
2020-12-03 21:33:53 +03:00
|
|
|
debug int // enable in order to have the unroll of the code 0 = NO_DEBUG, 1 = LIGHT 2 = VERBOSE
|
|
|
|
log_func FnLog = simple_log // log function, can be customized by the user
|
|
|
|
query string // query string
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-01-31 04:29:54 +03:00
|
|
|
// Reset RE object
|
2020-04-23 02:16:16 +03:00
|
|
|
//[inline]
|
2020-05-17 14:51:18 +03:00
|
|
|
fn (mut re RE) reset(){
|
2020-12-03 21:33:53 +03:00
|
|
|
re.cc_index = 0
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
mut i := 0
|
|
|
|
for i < re.prog.len {
|
2020-12-03 21:33:53 +03:00
|
|
|
re.prog[i].group_rep = 0 // clear repetition of the group
|
|
|
|
re.prog[i].rep = 0 // clear repetition of the token
|
2020-01-13 15:30:41 +03:00
|
|
|
i++
|
|
|
|
}
|
|
|
|
re.groups = [-1].repeat(re.group_count*2)
|
|
|
|
|
|
|
|
re.state_stack_index = -1
|
2020-01-25 21:12:23 +03:00
|
|
|
|
|
|
|
// reset group_csave
|
|
|
|
if re.group_csave.len > 0 {
|
|
|
|
re.group_csave_index = 1
|
2020-12-03 21:33:53 +03:00
|
|
|
re.group_csave[0] = 0 // reset the capture count
|
2020-01-25 21:12:23 +03:00
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-01-31 04:29:54 +03:00
|
|
|
// reset for search mode fail
|
|
|
|
// gcc bug, dont use [inline] or go 5 time slower
|
2020-05-17 14:51:18 +03:00
|
|
|
fn (mut re RE) reset_src(){
|
2020-01-31 04:29:54 +03:00
|
|
|
mut i := 0
|
|
|
|
for i < re.prog.len {
|
2020-12-03 21:33:53 +03:00
|
|
|
re.prog[i].group_rep = 0 // clear repetition of the group
|
|
|
|
re.prog[i].rep = 0 // clear repetition of the token
|
2020-01-31 04:29:54 +03:00
|
|
|
i++
|
|
|
|
}
|
|
|
|
re.state_stack_index = -1
|
|
|
|
}
|
|
|
|
|
2020-05-16 18:11:13 +03:00
|
|
|
// get_group get a group boundaries by its name
|
2020-01-28 22:34:11 +03:00
|
|
|
pub fn (re RE) get_group(group_name string) (int, int) {
|
|
|
|
if group_name in re.group_map {
|
|
|
|
tmp_index := re.group_map[group_name]-1
|
2020-12-03 21:33:53 +03:00
|
|
|
start := re.groups[tmp_index * 2]
|
|
|
|
end := re.groups[tmp_index * 2 + 1]
|
2020-01-28 22:34:11 +03:00
|
|
|
return start,end
|
|
|
|
}
|
|
|
|
return -1, -1
|
|
|
|
}
|
|
|
|
|
2020-06-08 00:04:23 +03:00
|
|
|
/*
|
|
|
|
|
|
|
|
Backslashes chars
|
|
|
|
|
|
|
|
*/
|
2020-01-13 15:30:41 +03:00
|
|
|
struct BslsStruct {
|
2020-08-27 07:46:18 +03:00
|
|
|
ch rune // meta char
|
2020-05-16 18:11:13 +03:00
|
|
|
validator FnValidator // validator function pointer
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
const(
|
2020-05-22 00:33:51 +03:00
|
|
|
bsls_validator_array = [
|
2020-01-13 15:30:41 +03:00
|
|
|
BslsStruct{`w`, is_alnum},
|
|
|
|
BslsStruct{`W`, is_not_alnum},
|
|
|
|
BslsStruct{`s`, is_space},
|
|
|
|
BslsStruct{`S`, is_not_space},
|
|
|
|
BslsStruct{`d`, is_digit},
|
|
|
|
BslsStruct{`D`, is_not_digit},
|
|
|
|
BslsStruct{`a`, is_lower},
|
|
|
|
BslsStruct{`A`, is_upper},
|
|
|
|
]
|
|
|
|
|
|
|
|
// these chars are escape if preceded by a \
|
2020-12-03 21:33:53 +03:00
|
|
|
bsls_escape_list = [`\\`, `|`, `.`, `*`, `+`, `-`, `{`, `}`, `[`, `]`]
|
2020-01-13 15:30:41 +03:00
|
|
|
)
|
|
|
|
|
|
|
|
enum BSLS_parse_state {
|
2020-04-23 02:16:16 +03:00
|
|
|
start
|
|
|
|
bsls_found
|
|
|
|
bsls_char
|
2020-01-13 15:30:41 +03:00
|
|
|
normal_char
|
|
|
|
}
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
// parse_bsls return (index, str_len) bsls_validator_array index, len of the backslash sequence if present
|
2020-01-13 15:30:41 +03:00
|
|
|
fn (re RE) parse_bsls(in_txt string, in_i int) (int,int){
|
|
|
|
mut status := BSLS_parse_state.start
|
|
|
|
mut i := in_i
|
|
|
|
|
|
|
|
for i < in_txt.len {
|
|
|
|
// get our char
|
2020-12-03 21:33:53 +03:00
|
|
|
char_tmp, char_len := re.get_char(in_txt, i)
|
2020-01-13 15:30:41 +03:00
|
|
|
ch := byte(char_tmp)
|
|
|
|
|
|
|
|
if status == .start && ch == `\\` {
|
|
|
|
status = .bsls_found
|
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// check if is our bsls char, for now only one length sequence
|
|
|
|
if status == .bsls_found {
|
2020-05-22 00:33:51 +03:00
|
|
|
for c,x in bsls_validator_array {
|
2020-01-13 15:30:41 +03:00
|
|
|
if x.ch == ch {
|
2020-12-03 21:33:53 +03:00
|
|
|
return c, i-in_i+1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
}
|
|
|
|
status = .normal_char
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// no BSLS validator, manage as normal escape char char
|
|
|
|
if status == .normal_char {
|
2020-05-22 00:33:51 +03:00
|
|
|
if ch in bsls_escape_list {
|
2020-12-03 21:33:53 +03:00
|
|
|
return no_match_found, i-in_i+1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-12-03 21:33:53 +03:00
|
|
|
return err_syntax_error, i-in_i+1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// at the present time we manage only one char after the \
|
|
|
|
break
|
|
|
|
|
|
|
|
}
|
|
|
|
// not our bsls return KO
|
2020-05-22 00:33:51 +03:00
|
|
|
return err_syntax_error, i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-06-08 00:04:23 +03:00
|
|
|
/*
|
|
|
|
|
|
|
|
Char class
|
|
|
|
|
|
|
|
*/
|
2020-01-13 15:30:41 +03:00
|
|
|
const(
|
2020-05-22 00:33:51 +03:00
|
|
|
cc_null = 0 // empty cc token
|
|
|
|
cc_char = 1 // simple char: a
|
|
|
|
cc_int = 2 // char interval: a-z
|
|
|
|
cc_bsls = 3 // backslash char
|
|
|
|
cc_end = 4 // cc sequence terminator
|
2020-01-13 15:30:41 +03:00
|
|
|
)
|
|
|
|
|
|
|
|
struct CharClass {
|
|
|
|
mut:
|
2020-12-03 21:33:53 +03:00
|
|
|
cc_type int = cc_null // type of cc token
|
|
|
|
ch0 rune // first char of the interval a-b a in this case
|
|
|
|
ch1 rune // second char of the interval a-b b in this case
|
|
|
|
validator FnValidator // validator function pointer
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
enum CharClass_parse_state {
|
2020-04-23 02:16:16 +03:00
|
|
|
start
|
|
|
|
in_char
|
|
|
|
in_bsls
|
|
|
|
separator
|
|
|
|
finish
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
fn (re RE) get_char_class(pc int) string {
|
2020-06-27 22:46:04 +03:00
|
|
|
buf := []byte{len:(re.cc.len)}
|
2020-04-25 23:42:48 +03:00
|
|
|
mut buf_ptr := &byte(&buf)
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
mut cc_i := re.prog[pc].cc_index
|
|
|
|
mut i := 0
|
|
|
|
mut tmp := 0
|
2020-05-22 00:33:51 +03:00
|
|
|
for cc_i >= 0 && cc_i < re.cc.len && re.cc[cc_i].cc_type != cc_end {
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
if re.cc[cc_i].cc_type == cc_bsls {
|
2020-07-22 20:28:53 +03:00
|
|
|
unsafe {
|
|
|
|
buf_ptr[i++] = `\\`
|
|
|
|
buf_ptr[i++] = byte(re.cc[cc_i].ch0)
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
else if re.cc[cc_i].ch0 == re.cc[cc_i].ch1 {
|
|
|
|
tmp = 3
|
|
|
|
for tmp >= 0 {
|
|
|
|
x := byte((re.cc[cc_i].ch0 >> (tmp*8)) & 0xFF)
|
2020-04-23 02:16:16 +03:00
|
|
|
if x != 0 {
|
2020-07-22 20:28:53 +03:00
|
|
|
unsafe {
|
|
|
|
buf_ptr[i++] = x
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
tmp--
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else {
|
|
|
|
tmp = 3
|
|
|
|
for tmp >= 0 {
|
|
|
|
x := byte((re.cc[cc_i].ch0 >> (tmp*8)) & 0xFF)
|
2020-04-23 02:16:16 +03:00
|
|
|
if x != 0 {
|
2020-07-22 20:28:53 +03:00
|
|
|
unsafe {
|
|
|
|
buf_ptr[i++] = x
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
tmp--
|
|
|
|
}
|
2020-07-22 20:28:53 +03:00
|
|
|
unsafe {
|
|
|
|
buf_ptr[i++] = `-`
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
tmp = 3
|
|
|
|
for tmp >= 0 {
|
|
|
|
x := byte((re.cc[cc_i].ch1 >> (tmp*8)) & 0xFF)
|
2020-04-23 02:16:16 +03:00
|
|
|
if x != 0 {
|
2020-07-22 20:28:53 +03:00
|
|
|
unsafe {
|
|
|
|
buf_ptr[i++] = x
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
tmp--
|
|
|
|
}
|
|
|
|
}
|
|
|
|
cc_i++
|
|
|
|
}
|
2020-07-22 20:28:53 +03:00
|
|
|
unsafe {
|
|
|
|
buf_ptr[i] = byte(0)
|
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
return tos_clone( buf_ptr )
|
|
|
|
}
|
|
|
|
|
2020-08-27 07:46:18 +03:00
|
|
|
fn (re RE) check_char_class(pc int, ch rune) bool {
|
2020-01-13 15:30:41 +03:00
|
|
|
mut cc_i := re.prog[pc].cc_index
|
2020-05-22 00:33:51 +03:00
|
|
|
for cc_i >= 0 && cc_i < re.cc.len && re.cc[cc_i].cc_type != cc_end {
|
|
|
|
if re.cc[cc_i].cc_type == cc_bsls {
|
2020-01-13 15:30:41 +03:00
|
|
|
if re.cc[cc_i].validator(byte(ch)) {
|
|
|
|
return true
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else if ch >= re.cc[cc_i].ch0 && ch <= re.cc[cc_i].ch1 {
|
|
|
|
return true
|
|
|
|
}
|
|
|
|
cc_i++
|
|
|
|
}
|
|
|
|
return false
|
|
|
|
}
|
|
|
|
|
|
|
|
// parse_char_class return (index, str_len, cc_type) of a char class [abcm-p], char class start after the [ char
|
2020-08-27 07:46:18 +03:00
|
|
|
fn (mut re RE) parse_char_class(in_txt string, in_i int) (int, int, rune) {
|
2020-01-13 15:30:41 +03:00
|
|
|
mut status := CharClass_parse_state.start
|
|
|
|
mut i := in_i
|
|
|
|
|
|
|
|
mut tmp_index := re.cc_index
|
2020-12-03 21:33:53 +03:00
|
|
|
res_index := re.cc_index
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
mut cc_type := u32(ist_char_class_pos)
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
for i < in_txt.len {
|
|
|
|
|
|
|
|
// check if we are out of memory for char classes
|
|
|
|
if tmp_index >= re.cc.len {
|
2020-12-03 21:33:53 +03:00
|
|
|
return err_cc_alloc_overflow, 0, u32(0)
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// get our char
|
2020-01-16 02:39:33 +03:00
|
|
|
char_tmp,char_len := re.get_char(in_txt,i)
|
2020-01-13 15:30:41 +03:00
|
|
|
ch := byte(char_tmp)
|
|
|
|
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("CC #${i:3d} ch: ${ch:c}")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// negation
|
|
|
|
if status == .start && ch == `^` {
|
2020-05-22 00:33:51 +03:00
|
|
|
cc_type = u32(ist_char_class_neg)
|
2020-01-13 15:30:41 +03:00
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-05-16 18:11:13 +03:00
|
|
|
// minus symbol
|
|
|
|
if status == .start && ch == `-` {
|
2020-05-22 00:33:51 +03:00
|
|
|
re.cc[tmp_index].cc_type = cc_char
|
2020-05-16 18:11:13 +03:00
|
|
|
re.cc[tmp_index].ch0 = char_tmp
|
|
|
|
re.cc[tmp_index].ch1 = char_tmp
|
|
|
|
i += char_len
|
|
|
|
tmp_index++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// bsls
|
|
|
|
if (status == .start || status == .in_char) && ch == `\\` {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("CC bsls.")
|
2020-01-13 15:30:41 +03:00
|
|
|
status = .in_bsls
|
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
if status == .in_bsls {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("CC bsls validation.")
|
2020-05-22 00:33:51 +03:00
|
|
|
for c,x in bsls_validator_array {
|
2020-01-13 15:30:41 +03:00
|
|
|
if x.ch == ch {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("CC bsls found [${ch:c}]")
|
2020-05-22 00:33:51 +03:00
|
|
|
re.cc[tmp_index].cc_type = cc_bsls
|
|
|
|
re.cc[tmp_index].ch0 = bsls_validator_array[c].ch
|
|
|
|
re.cc[tmp_index].ch1 = bsls_validator_array[c].ch
|
|
|
|
re.cc[tmp_index].validator = bsls_validator_array[c].validator
|
2020-01-13 15:30:41 +03:00
|
|
|
i += char_len
|
|
|
|
tmp_index++
|
|
|
|
status = .in_char
|
|
|
|
break
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if status == .in_bsls {
|
2020-12-05 03:51:48 +03:00
|
|
|
//println("CC bsls not found [${ch:c}]")
|
2020-01-13 15:30:41 +03:00
|
|
|
status = .in_char
|
|
|
|
}else {
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// simple char
|
2020-04-23 02:16:16 +03:00
|
|
|
if (status == .start || status == .in_char) &&
|
|
|
|
ch != `-` && ch != `]`
|
2020-01-13 15:30:41 +03:00
|
|
|
{
|
|
|
|
status = .in_char
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
re.cc[tmp_index].cc_type = cc_char
|
2020-01-13 15:30:41 +03:00
|
|
|
re.cc[tmp_index].ch0 = char_tmp
|
|
|
|
re.cc[tmp_index].ch1 = char_tmp
|
|
|
|
|
|
|
|
i += char_len
|
|
|
|
tmp_index++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// check range separator
|
|
|
|
if status == .in_char && ch == `-` {
|
|
|
|
status = .separator
|
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// check range end
|
|
|
|
if status == .separator && ch != `]` && ch != `-` {
|
|
|
|
status = .in_char
|
2020-05-22 00:33:51 +03:00
|
|
|
re.cc[tmp_index-1].cc_type = cc_int
|
2020-01-13 15:30:41 +03:00
|
|
|
re.cc[tmp_index-1].ch1 = char_tmp
|
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// char class end
|
|
|
|
if status == .in_char && ch == `]` {
|
2020-05-22 00:33:51 +03:00
|
|
|
re.cc[tmp_index].cc_type = cc_end
|
2020-01-13 15:30:41 +03:00
|
|
|
re.cc[tmp_index].ch0 = 0
|
|
|
|
re.cc[tmp_index].ch1 = 0
|
|
|
|
re.cc_index = tmp_index+1
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
return res_index, i-in_i+2, cc_type
|
|
|
|
}
|
|
|
|
|
|
|
|
i++
|
|
|
|
}
|
2020-05-22 00:33:51 +03:00
|
|
|
return err_syntax_error,0,u32(0)
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-06-08 00:04:23 +03:00
|
|
|
/*
|
|
|
|
|
|
|
|
Re Compiler
|
|
|
|
|
|
|
|
*/
|
2020-01-13 15:30:41 +03:00
|
|
|
//
|
|
|
|
// Quantifier
|
|
|
|
//
|
|
|
|
enum Quant_parse_state {
|
2020-04-23 02:16:16 +03:00
|
|
|
start
|
|
|
|
min_parse
|
|
|
|
comma_checked
|
|
|
|
max_parse
|
|
|
|
greedy
|
|
|
|
gredy_parse
|
2020-01-13 15:30:41 +03:00
|
|
|
finish
|
|
|
|
}
|
|
|
|
|
2020-01-28 22:34:11 +03:00
|
|
|
// parse_quantifier return (min, max, str_len, greedy_flag) of a {min,max}? quantifier starting after the { char
|
2020-01-16 02:39:33 +03:00
|
|
|
fn (re RE) parse_quantifier(in_txt string, in_i int) (int, int, int, bool) {
|
2020-01-13 15:30:41 +03:00
|
|
|
mut status := Quant_parse_state.start
|
|
|
|
mut i := in_i
|
|
|
|
|
|
|
|
mut q_min := 0 // default min in a {} quantifier is 1
|
2020-05-22 00:33:51 +03:00
|
|
|
mut q_max := 0 // deafult max in a {} quantifier is max_quantifier
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
mut ch := byte(0)
|
|
|
|
|
|
|
|
for i < in_txt.len {
|
2020-07-22 20:28:53 +03:00
|
|
|
unsafe {
|
|
|
|
ch = in_txt.str[i]
|
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("${ch:c} status: $status")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// exit on no compatible char with {} quantifier
|
|
|
|
if utf8util_char_len(ch) != 1 {
|
2020-12-03 21:33:53 +03:00
|
|
|
return err_syntax_error, i, 0, false
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// min parsing skip if comma present
|
|
|
|
if status == .start && ch == `,` {
|
2020-01-18 09:38:00 +03:00
|
|
|
q_min = 0 // default min in a {} quantifier is 0
|
2020-01-13 15:30:41 +03:00
|
|
|
status = .comma_checked
|
|
|
|
i++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
if status == .start && is_digit( ch ) {
|
|
|
|
status = .min_parse
|
|
|
|
q_min *= 10
|
|
|
|
q_min += int(ch - `0`)
|
|
|
|
i++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
if status == .min_parse && is_digit( ch ) {
|
|
|
|
q_min *= 10
|
|
|
|
q_min += int(ch - `0`)
|
|
|
|
i++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// we have parsed the min, now check the max
|
|
|
|
if status == .min_parse && ch == `,` {
|
|
|
|
status = .comma_checked
|
|
|
|
i++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// single value {4}
|
|
|
|
if status == .min_parse && ch == `}` {
|
|
|
|
q_max = q_min
|
2020-01-16 02:39:33 +03:00
|
|
|
|
|
|
|
status = .greedy
|
|
|
|
continue
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// end without max
|
|
|
|
if status == .comma_checked && ch == `}` {
|
2020-05-22 00:33:51 +03:00
|
|
|
q_max = max_quantifier
|
2020-01-16 02:39:33 +03:00
|
|
|
|
|
|
|
status = .greedy
|
|
|
|
continue
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// start max parsing
|
|
|
|
if status == .comma_checked && is_digit( ch ) {
|
|
|
|
status = .max_parse
|
|
|
|
q_max *= 10
|
|
|
|
q_max += int(ch - `0`)
|
|
|
|
i++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// parse the max
|
|
|
|
if status == .max_parse && is_digit( ch ) {
|
|
|
|
q_max *= 10
|
|
|
|
q_max += int(ch - `0`)
|
|
|
|
i++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-01-16 02:39:33 +03:00
|
|
|
// finished the quantifier
|
2020-01-13 15:30:41 +03:00
|
|
|
if status == .max_parse && ch == `}` {
|
2020-01-16 02:39:33 +03:00
|
|
|
status = .greedy
|
|
|
|
continue
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-01-16 02:39:33 +03:00
|
|
|
|
|
|
|
// check if greedy flag char ? is present
|
|
|
|
if status == .greedy {
|
|
|
|
if i+1 < in_txt.len {
|
|
|
|
i++
|
|
|
|
status = .gredy_parse
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
return q_min, q_max, i-in_i+2, false
|
|
|
|
}
|
|
|
|
|
|
|
|
// check the greedy flag
|
|
|
|
if status == .gredy_parse {
|
|
|
|
if ch == `?` {
|
|
|
|
return q_min, q_max, i-in_i+2, true
|
|
|
|
} else {
|
|
|
|
i--
|
|
|
|
return q_min, q_max, i-in_i+2, false
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// not a {} quantifier, exit
|
2020-05-22 00:33:51 +03:00
|
|
|
return err_syntax_error, i, 0, false
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// not a conform {} quantifier
|
2020-05-22 00:33:51 +03:00
|
|
|
return err_syntax_error, i, 0, false
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-01-28 22:34:11 +03:00
|
|
|
//
|
|
|
|
// Groups
|
|
|
|
//
|
|
|
|
enum Group_parse_state {
|
2020-04-23 02:16:16 +03:00
|
|
|
start
|
|
|
|
q_mark // (?
|
|
|
|
q_mark1 // (?:|P checking
|
|
|
|
p_status // (?P
|
|
|
|
p_start // (?P<
|
|
|
|
p_end // (?P<...>
|
|
|
|
p_in_name // (?P<...
|
2020-01-28 22:34:11 +03:00
|
|
|
finish
|
|
|
|
}
|
|
|
|
|
|
|
|
// parse_groups parse a group for ? (question mark) syntax, if found, return (error, capture_flag, name_of_the_group, next_index)
|
|
|
|
fn (re RE) parse_groups(in_txt string, in_i int) (int, bool, string, int) {
|
|
|
|
mut status := Group_parse_state.start
|
|
|
|
mut i := in_i
|
|
|
|
mut name := ''
|
|
|
|
|
|
|
|
for i < in_txt.len && status != .finish {
|
|
|
|
|
|
|
|
// get our char
|
|
|
|
char_tmp,char_len := re.get_char(in_txt,i)
|
|
|
|
ch := byte(char_tmp)
|
|
|
|
|
|
|
|
// start
|
|
|
|
if status == .start && ch == `(` {
|
|
|
|
status = .q_mark
|
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// check for question marks
|
|
|
|
if status == .q_mark && ch == `?` {
|
|
|
|
status = .q_mark1
|
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// non capturing group
|
|
|
|
if status == .q_mark1 && ch == `:` {
|
|
|
|
i += char_len
|
|
|
|
return 0, false, name, i
|
|
|
|
}
|
|
|
|
|
|
|
|
// enter in P section
|
|
|
|
if status == .q_mark1 && ch == `P` {
|
|
|
|
status = .p_status
|
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// not a valid q mark found
|
|
|
|
if status == .q_mark1 {
|
|
|
|
//println("NO VALID Q MARK")
|
|
|
|
return -2 , true, name, i
|
|
|
|
}
|
|
|
|
|
|
|
|
if status == .p_status && ch == `<` {
|
|
|
|
status = .p_start
|
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
if status == .p_start && ch != `>` {
|
|
|
|
status = .p_in_name
|
|
|
|
name += "${ch:1c}" // TODO: manage utf8 chars
|
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// colect name
|
|
|
|
if status == .p_in_name && ch != `>` && is_alnum(ch) {
|
|
|
|
name += "${ch:1c}" // TODO: manage utf8 chars
|
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// end name
|
|
|
|
if status == .p_in_name && ch == `>` {
|
|
|
|
i += char_len
|
|
|
|
return 0, true, name, i
|
|
|
|
}
|
|
|
|
|
|
|
|
// error on name group
|
|
|
|
if status == .p_in_name {
|
|
|
|
return -2 , true, name, i
|
|
|
|
}
|
|
|
|
|
|
|
|
// normal group, nothig to do, exit
|
|
|
|
return 0 , true, name, i
|
|
|
|
}
|
|
|
|
/* UNREACHABLE */
|
|
|
|
//println("ERROR!! NOT MEANT TO BE HERE!!1")
|
|
|
|
return -2 , true, name, i
|
|
|
|
}
|
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
//
|
|
|
|
// main compiler
|
|
|
|
//
|
|
|
|
// compile return (return code, index) where index is the index of the error in the query string if return code is an error code
|
2020-08-08 09:04:12 +03:00
|
|
|
[deprecated]
|
2020-12-03 21:33:53 +03:00
|
|
|
pub fn (mut re RE) compile(in_txt string) (int, int) {
|
2020-08-08 09:04:12 +03:00
|
|
|
return re.impl_compile(in_txt)
|
2020-08-27 07:46:18 +03:00
|
|
|
}
|
2020-08-08 09:04:12 +03:00
|
|
|
|
|
|
|
fn (mut re RE) impl_compile(in_txt string) (int,int) {
|
2020-01-13 15:30:41 +03:00
|
|
|
mut i := 0 // input string index
|
|
|
|
mut pc := 0 // program counter
|
|
|
|
|
|
|
|
// group management variables
|
|
|
|
mut group_count := -1
|
|
|
|
mut group_stack := [0 ].repeat(re.group_max_nested)
|
|
|
|
mut group_stack_txt_index := [-1].repeat(re.group_max_nested)
|
|
|
|
mut group_stack_index := -1
|
|
|
|
|
|
|
|
re.query = in_txt // save the query string
|
|
|
|
|
|
|
|
i = 0
|
|
|
|
for i < in_txt.len {
|
|
|
|
mut char_tmp := u32(0)
|
|
|
|
mut char_len := 0
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("i: ${i:3d} ch: ${in_txt.str[i]:c}")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-01-16 02:39:33 +03:00
|
|
|
char_tmp,char_len = re.get_char(in_txt,i)
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
//
|
|
|
|
// check special cases: $ ^
|
|
|
|
//
|
|
|
|
if char_len == 1 && i == 0 && byte(char_tmp) == `^` {
|
2020-05-22 00:33:51 +03:00
|
|
|
re.flag = f_ms
|
2020-01-13 15:30:41 +03:00
|
|
|
i = i + char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
if char_len == 1 && i == (in_txt.len-1) && byte(char_tmp) == `$` {
|
2020-05-22 00:33:51 +03:00
|
|
|
re.flag = f_me
|
2020-01-13 15:30:41 +03:00
|
|
|
i = i + char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
// ist_group_start
|
2020-01-13 15:30:41 +03:00
|
|
|
if char_len == 1 && pc >= 0 && byte(char_tmp) == `(` {
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
//check max groups allowed
|
|
|
|
if group_count > re.group_max {
|
2020-12-03 21:33:53 +03:00
|
|
|
return err_groups_overflow, i+1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
group_stack_index++
|
|
|
|
|
|
|
|
// check max nested groups allowed
|
|
|
|
if group_stack_index > re.group_max_nested {
|
2020-12-03 21:33:53 +03:00
|
|
|
return err_groups_max_nested, i+1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-01-28 22:34:11 +03:00
|
|
|
tmp_res, cgroup_flag, cgroup_name, next_i := re.parse_groups(in_txt,i)
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-28 22:34:11 +03:00
|
|
|
// manage question mark format error
|
|
|
|
if tmp_res < -1 {
|
2020-12-03 21:33:53 +03:00
|
|
|
return err_group_qm_notation, next_i
|
2020-01-28 22:34:11 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
//println("Parse group: [$tmp_res, $cgroup_flag, ($i,$next_i), '${in_txt[i..next_i]}' ]")
|
|
|
|
i = next_i
|
|
|
|
|
|
|
|
if cgroup_flag == true {
|
|
|
|
group_count++
|
|
|
|
}
|
|
|
|
|
|
|
|
// calculate the group id
|
|
|
|
// if it is a named group, recycle the group id
|
|
|
|
// NOTE: **** the group index is +1 because map return 0 when not found!! ****
|
|
|
|
mut group_id := group_count
|
|
|
|
if cgroup_name.len > 0 {
|
|
|
|
//println("GROUP NAME: ${cgroup_name}")
|
|
|
|
if cgroup_name in re.group_map{
|
2020-12-03 21:33:53 +03:00
|
|
|
group_id = re.group_map[cgroup_name] - 1
|
2020-01-28 22:34:11 +03:00
|
|
|
group_count--
|
|
|
|
} else {
|
2020-12-03 21:33:53 +03:00
|
|
|
re.group_map[cgroup_name] = group_id + 1
|
2020-01-28 22:34:11 +03:00
|
|
|
}
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
group_stack_txt_index[group_stack_index] = i
|
|
|
|
group_stack[group_stack_index] = pc
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
re.prog[pc].ist = u32(0) | ist_group_start
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[pc].rep_min = 1
|
|
|
|
re.prog[pc].rep_max = 1
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-28 22:34:11 +03:00
|
|
|
// set the group id
|
|
|
|
if cgroup_flag == false {
|
|
|
|
//println("NO CAPTURE GROUP")
|
2020-04-23 02:16:16 +03:00
|
|
|
re.prog[pc].group_id = -1
|
2020-01-28 22:34:11 +03:00
|
|
|
} else {
|
|
|
|
re.prog[pc].group_id = group_id
|
|
|
|
}
|
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
pc = pc + 1
|
|
|
|
continue
|
|
|
|
|
|
|
|
}
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
// ist_group_end
|
2020-01-13 15:30:41 +03:00
|
|
|
if char_len==1 && pc > 0 && byte(char_tmp) == `)` {
|
|
|
|
if group_stack_index < 0 {
|
2020-12-03 21:33:53 +03:00
|
|
|
return err_group_not_balanced, i+1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
goto_pc := group_stack[group_stack_index]
|
|
|
|
group_stack_index--
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
re.prog[pc].ist = u32(0) | ist_group_end
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[pc].rep_min = 1
|
|
|
|
re.prog[pc].rep_max = 1
|
|
|
|
|
|
|
|
re.prog[pc].goto_pc = goto_pc // PC where to jump if a group need
|
|
|
|
re.prog[pc].group_id = re.prog[goto_pc].group_id // id of this group, used for storing data
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[goto_pc].goto_pc = pc // start goto point to the end group pc
|
|
|
|
//re.prog[goto_pc].group_id = group_count // id of this group, used for storing data
|
|
|
|
|
|
|
|
pc = pc + 1
|
|
|
|
i = i + char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
// ist_dot_char match any char except the following token
|
2020-01-13 15:30:41 +03:00
|
|
|
if char_len==1 && pc >= 0 && byte(char_tmp) == `.` {
|
2020-05-22 00:33:51 +03:00
|
|
|
re.prog[pc].ist = u32(0) | ist_dot_char
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[pc].rep_min = 1
|
|
|
|
re.prog[pc].rep_max = 1
|
|
|
|
pc = pc + 1
|
|
|
|
i = i + char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// OR branch
|
|
|
|
if char_len==1 && pc > 0 && byte(char_tmp) == `|` {
|
2020-05-22 00:33:51 +03:00
|
|
|
// two consecutive ist_dot_char are an error
|
|
|
|
if pc > 0 && re.prog[pc-1].ist == ist_or_branch {
|
|
|
|
return err_syntax_error,i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-05-22 00:33:51 +03:00
|
|
|
re.prog[pc].ist = u32(0) | ist_or_branch
|
2020-01-13 15:30:41 +03:00
|
|
|
pc = pc + 1
|
|
|
|
i = i + char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// Quantifiers
|
|
|
|
if char_len==1 && pc > 0{
|
|
|
|
mut quant_flag := true
|
|
|
|
match byte(char_tmp) {
|
|
|
|
`?` {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("q: ${char_tmp:c}")
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[pc-1].rep_min = 0
|
|
|
|
re.prog[pc-1].rep_max = 1
|
|
|
|
}
|
|
|
|
|
|
|
|
`+` {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("q: ${char_tmp:c}")
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[pc-1].rep_min = 1
|
2020-05-22 00:33:51 +03:00
|
|
|
re.prog[pc-1].rep_max = max_quantifier
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
`*` {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("q: ${char_tmp:c}")
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[pc-1].rep_min = 0
|
2020-05-22 00:33:51 +03:00
|
|
|
re.prog[pc-1].rep_max = max_quantifier
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
`{` {
|
2020-01-16 02:39:33 +03:00
|
|
|
min, max, tmp, greedy := re.parse_quantifier(in_txt, i+1)
|
2020-01-13 15:30:41 +03:00
|
|
|
// it is a quantifier
|
|
|
|
if min >= 0 {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("{$min,$max}\n str:[${in_txt[i..i+tmp]}] greedy:$greedy")
|
2020-01-13 15:30:41 +03:00
|
|
|
i = i + tmp
|
|
|
|
re.prog[pc-1].rep_min = min
|
|
|
|
re.prog[pc-1].rep_max = max
|
2020-01-16 02:39:33 +03:00
|
|
|
re.prog[pc-1].greedy = greedy
|
2020-01-13 15:30:41 +03:00
|
|
|
continue
|
|
|
|
}
|
|
|
|
else {
|
|
|
|
return min,i
|
|
|
|
}
|
|
|
|
// TODO: decide if the open bracket can be conform without the close bracket
|
|
|
|
/*
|
|
|
|
// no conform, parse as normal char
|
|
|
|
else {
|
|
|
|
quant_flag = false
|
|
|
|
}
|
|
|
|
*/
|
|
|
|
}
|
|
|
|
else{
|
|
|
|
quant_flag = false
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if quant_flag {
|
|
|
|
i = i + char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-01-16 02:39:33 +03:00
|
|
|
// IST_CHAR_CLASS_*
|
2020-01-13 15:30:41 +03:00
|
|
|
if char_len==1 && pc >= 0{
|
|
|
|
if byte(char_tmp) == `[` {
|
|
|
|
cc_index,tmp,cc_type := re.parse_char_class(in_txt, i+1)
|
|
|
|
if cc_index >= 0 {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("index: $cc_index str:${in_txt[i..i+tmp]}")
|
2020-01-13 15:30:41 +03:00
|
|
|
i = i + tmp
|
|
|
|
re.prog[pc].ist = u32(0) | cc_type
|
|
|
|
re.prog[pc].cc_index = cc_index
|
|
|
|
re.prog[pc].rep_min = 1
|
|
|
|
re.prog[pc].rep_max = 1
|
|
|
|
pc = pc + 1
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// cc_class vector memory full
|
|
|
|
else if cc_index < 0 {
|
|
|
|
return cc_index, i
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
// ist_bsls_char
|
2020-01-13 15:30:41 +03:00
|
|
|
if char_len==1 && pc >= 0{
|
|
|
|
if byte(char_tmp) == `\\` {
|
|
|
|
bsls_index,tmp := re.parse_bsls(in_txt,i)
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("index: $bsls_index str:${in_txt[i..i+tmp]}")
|
2020-01-13 15:30:41 +03:00
|
|
|
if bsls_index >= 0 {
|
|
|
|
i = i + tmp
|
2020-05-22 00:33:51 +03:00
|
|
|
re.prog[pc].ist = u32(0) | ist_bsls_char
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[pc].rep_min = 1
|
|
|
|
re.prog[pc].rep_max = 1
|
2020-05-22 00:33:51 +03:00
|
|
|
re.prog[pc].validator = bsls_validator_array[bsls_index].validator
|
|
|
|
re.prog[pc].ch = bsls_validator_array[bsls_index].ch
|
2020-01-13 15:30:41 +03:00
|
|
|
pc = pc + 1
|
|
|
|
continue
|
2020-04-23 02:16:16 +03:00
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
// this is an escape char, skip the bsls and continue as a normal char
|
2020-05-22 00:33:51 +03:00
|
|
|
else if bsls_index == no_match_found {
|
2020-01-13 15:30:41 +03:00
|
|
|
i += char_len
|
2020-01-16 02:39:33 +03:00
|
|
|
char_tmp,char_len = re.get_char(in_txt,i)
|
2020-01-13 15:30:41 +03:00
|
|
|
// continue as simple char
|
|
|
|
}
|
|
|
|
// if not an escape or a bsls char then it is an error (at least for now!)
|
|
|
|
else {
|
2020-12-03 21:33:53 +03:00
|
|
|
return bsls_index, i+tmp
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
// ist_simple_char
|
|
|
|
re.prog[pc].ist = ist_simple_char
|
2020-01-16 02:39:33 +03:00
|
|
|
re.prog[pc].ch = char_tmp
|
2020-05-24 22:07:32 +03:00
|
|
|
re.prog[pc].ch_len = byte(char_len)
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[pc].rep_min = 1
|
|
|
|
re.prog[pc].rep_max = 1
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("char: ${char_tmp:c}")
|
2020-01-13 15:30:41 +03:00
|
|
|
pc = pc +1
|
|
|
|
|
|
|
|
i+=char_len
|
|
|
|
}
|
|
|
|
|
|
|
|
// add end of the program
|
2020-05-22 00:33:51 +03:00
|
|
|
re.prog[pc].ist = ist_prog_end
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// check for unbalanced groups
|
|
|
|
if group_stack_index != -1 {
|
2020-05-22 00:33:51 +03:00
|
|
|
return err_group_not_balanced, group_stack_txt_index[group_stack_index]+1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// check for OR at the end of the program
|
2020-05-22 00:33:51 +03:00
|
|
|
if pc > 0 && re.prog[pc-1].ist == ist_or_branch {
|
|
|
|
return err_syntax_error,in_txt.len
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// store the number of groups in the query
|
2020-12-03 21:33:53 +03:00
|
|
|
re.group_count = group_count + 1
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
//******************************************
|
|
|
|
// Post processing
|
|
|
|
//******************************************
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
// count ist_dot_char to set the size of the state stack
|
2020-01-13 15:30:41 +03:00
|
|
|
mut pc1 := 0
|
|
|
|
mut tmp_count := 0
|
|
|
|
for pc1 < pc {
|
2020-05-22 00:33:51 +03:00
|
|
|
if re.prog[pc1].ist == ist_dot_char {
|
2020-01-13 15:30:41 +03:00
|
|
|
tmp_count++
|
|
|
|
}
|
|
|
|
pc1++
|
|
|
|
}
|
2020-01-18 09:38:00 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// init the state stack
|
2020-09-08 16:15:35 +03:00
|
|
|
re.state_stack = []StateDotObj{len: tmp_count+1, init: StateDotObj{}}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// OR branch
|
|
|
|
// a|b|cd
|
|
|
|
// d exit point
|
|
|
|
// a,b,c branches
|
|
|
|
// set the jump in the right places
|
|
|
|
pc1 = 0
|
|
|
|
for pc1 < pc-2 {
|
2020-12-05 03:51:48 +03:00
|
|
|
//println("Here $pc1 ${pc-2}")
|
2020-01-13 15:30:41 +03:00
|
|
|
// two consecutive OR are a syntax error
|
2020-05-22 00:33:51 +03:00
|
|
|
if re.prog[pc1+1].ist == ist_or_branch && re.prog[pc1+2].ist == ist_or_branch {
|
|
|
|
return err_syntax_error, i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// manange a|b chains like a|(b)|c|d...
|
|
|
|
// standard solution
|
2020-05-22 00:33:51 +03:00
|
|
|
if re.prog[pc1].ist != ist_or_branch &&
|
|
|
|
re.prog[pc1+1].ist == ist_or_branch &&
|
|
|
|
re.prog[pc1+2].ist != ist_or_branch
|
2020-01-13 15:30:41 +03:00
|
|
|
{
|
|
|
|
re.prog[pc1].next_is_or = true // set that the next token is an OR
|
|
|
|
re.prog[pc1+1].rep_min = pc1+2 // failed match jump
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// match jump, if an OR chain the next token will be an OR token
|
|
|
|
mut pc2 := pc1+2
|
|
|
|
for pc2 < pc-1 {
|
|
|
|
ist := re.prog[pc2].ist
|
2020-05-22 00:33:51 +03:00
|
|
|
if ist == ist_group_start {
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[pc1+1].rep_max = re.prog[pc2].goto_pc + 1
|
|
|
|
break
|
|
|
|
}
|
2020-05-22 00:33:51 +03:00
|
|
|
if ist != ist_or_branch {
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[pc1+1].rep_max = pc2 + 1
|
|
|
|
break
|
|
|
|
}
|
2020-12-05 03:51:48 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
pc2++
|
|
|
|
}
|
2020-12-05 03:51:48 +03:00
|
|
|
// special case query of few chars, teh true can't go on the first instruction
|
|
|
|
if re.prog[pc1+1].rep_max == pc1 {
|
|
|
|
re.prog[pc1+1].rep_max = 3
|
|
|
|
}
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("Compile OR postproc. [$pc1,OR ${pc1+1},$pc2]")
|
2020-04-23 02:16:16 +03:00
|
|
|
pc1 = pc2
|
2020-01-13 15:30:41 +03:00
|
|
|
continue
|
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
pc1++
|
|
|
|
}
|
|
|
|
|
|
|
|
//******************************************
|
|
|
|
// DEBUG PRINT REGEX GENERATED CODE
|
|
|
|
//******************************************
|
|
|
|
if re.debug > 0 {
|
2020-04-25 23:42:48 +03:00
|
|
|
gc := re.get_code()
|
|
|
|
re.log_func( gc )
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
//******************************************
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
return compile_ok, 0
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// get_code return the compiled code as regex string, note: may be different from the source!
|
|
|
|
pub fn (re RE) get_code() string {
|
|
|
|
mut pc1 := 0
|
2020-01-14 04:45:08 +03:00
|
|
|
mut res := strings.new_builder(re.cc.len*2*re.prog.len)
|
2020-05-22 00:33:51 +03:00
|
|
|
res.write("========================================\nv RegEx compiler v $v_regex_version output:\n")
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
mut stop_flag := false
|
|
|
|
|
|
|
|
for pc1 <= re.prog.len {
|
2020-01-25 21:12:23 +03:00
|
|
|
tk := re.prog[pc1]
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("PC:${pc1:3d}")
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write(" ist: ")
|
2020-01-25 21:12:23 +03:00
|
|
|
res.write("${tk.ist:8x}".replace(" ","0") )
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write(" ")
|
2020-01-25 21:12:23 +03:00
|
|
|
ist :=tk.ist
|
2020-05-22 00:33:51 +03:00
|
|
|
if ist == ist_bsls_char {
|
2020-01-25 21:12:23 +03:00
|
|
|
res.write("[\\${tk.ch:1c}] BSLS")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_prog_end {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("PROG_END")
|
2020-01-13 15:30:41 +03:00
|
|
|
stop_flag = true
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_or_branch {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("OR ")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_char_class_pos {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("[${re.get_char_class(pc1)}] CHAR_CLASS_POS")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_char_class_neg {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("[^${re.get_char_class(pc1)}] CHAR_CLASS_NEG")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_dot_char {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write(". DOT_CHAR")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_group_start {
|
2020-01-25 21:12:23 +03:00
|
|
|
res.write("( GROUP_START #:${tk.group_id}")
|
2020-01-28 22:34:11 +03:00
|
|
|
if tk.group_id == -1 {
|
|
|
|
res.write(" ?:")
|
|
|
|
} else {
|
|
|
|
for x in re.group_map.keys() {
|
|
|
|
if re.group_map[x] == (tk.group_id+1) {
|
|
|
|
res.write(" ?P<${x}>")
|
|
|
|
break
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_group_end {
|
2020-01-25 21:12:23 +03:00
|
|
|
res.write(") GROUP_END #:${tk.group_id}")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_simple_char {
|
2020-01-25 21:12:23 +03:00
|
|
|
res.write("[${tk.ch:1c}] query_ch")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
if tk.rep_max == max_quantifier {
|
2020-01-25 21:12:23 +03:00
|
|
|
res.write(" {${tk.rep_min:3d},MAX}")
|
2020-01-13 15:30:41 +03:00
|
|
|
}else{
|
2020-05-22 00:33:51 +03:00
|
|
|
if ist == ist_or_branch {
|
2020-01-25 21:12:23 +03:00
|
|
|
res.write(" if false go: ${tk.rep_min:3d} if true go: ${tk.rep_max:3d}")
|
2020-01-13 15:30:41 +03:00
|
|
|
} else {
|
2020-01-25 21:12:23 +03:00
|
|
|
res.write(" {${tk.rep_min:3d},${tk.rep_max:3d}}")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-01-25 21:12:23 +03:00
|
|
|
if tk.greedy == true {
|
2020-01-16 02:39:33 +03:00
|
|
|
res.write("?")
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("\n")
|
2020-01-13 15:30:41 +03:00
|
|
|
if stop_flag {
|
|
|
|
break
|
|
|
|
}
|
|
|
|
pc1++
|
|
|
|
}
|
|
|
|
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("========================================\n")
|
|
|
|
return res.str()
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// get_query return a string with a reconstruction of the query starting from the regex program code
|
|
|
|
pub fn (re RE) get_query() string {
|
2020-01-14 04:45:08 +03:00
|
|
|
mut res := strings.new_builder(re.query.len*2)
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
if (re.flag & f_ms) != 0 {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("^")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
mut i := 0
|
2020-05-22 00:33:51 +03:00
|
|
|
for i < re.prog.len && re.prog[i].ist != ist_prog_end && re.prog[i].ist != 0{
|
2020-10-05 14:08:30 +03:00
|
|
|
tk := unsafe { &re.prog[i] }
|
2020-01-25 21:12:23 +03:00
|
|
|
ch := tk.ist
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// GROUP start
|
2020-05-22 00:33:51 +03:00
|
|
|
if ch == ist_group_start {
|
2020-01-13 15:30:41 +03:00
|
|
|
if re.debug == 0 {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("(")
|
2020-01-13 15:30:41 +03:00
|
|
|
} else {
|
2020-01-28 22:34:11 +03:00
|
|
|
if tk.group_id == -1 {
|
|
|
|
res.write("(?:") // non capturing group
|
|
|
|
} else {
|
|
|
|
res.write("#${tk.group_id}(")
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-28 22:34:11 +03:00
|
|
|
for x in re.group_map.keys() {
|
|
|
|
if re.group_map[x] == (tk.group_id+1) {
|
|
|
|
res.write("?P<${x}>")
|
|
|
|
break
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
i++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// GROUP end
|
2020-05-22 00:33:51 +03:00
|
|
|
if ch == ist_group_end {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write(")")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// OR branch
|
2020-05-22 00:33:51 +03:00
|
|
|
if ch == ist_or_branch {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("|")
|
2020-01-13 15:30:41 +03:00
|
|
|
if re.debug > 0 {
|
2020-01-25 21:12:23 +03:00
|
|
|
res.write("{${tk.rep_min},${tk.rep_max}}")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
i++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// char class
|
2020-05-22 00:33:51 +03:00
|
|
|
if ch == ist_char_class_neg || ch == ist_char_class_pos {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("[")
|
2020-05-22 00:33:51 +03:00
|
|
|
if ch == ist_char_class_neg {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("^")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("${re.get_char_class(i)}")
|
|
|
|
res.write("]")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// bsls char
|
2020-05-22 00:33:51 +03:00
|
|
|
if ch == ist_bsls_char {
|
2020-01-25 21:12:23 +03:00
|
|
|
res.write("\\${tk.ch:1c}")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
// ist_dot_char
|
|
|
|
if ch == ist_dot_char {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write(".")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// char alone
|
2020-05-22 00:33:51 +03:00
|
|
|
if ch == ist_simple_char {
|
|
|
|
if byte(ch) in bsls_escape_list {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("\\")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-01-25 21:12:23 +03:00
|
|
|
res.write("${tk.ch:c}")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// quantifier
|
2020-01-25 21:12:23 +03:00
|
|
|
if !(tk.rep_min == 1 && tk.rep_max == 1) {
|
|
|
|
if tk.rep_min == 0 && tk.rep_max == 1 {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("?")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if tk.rep_min == 1 && tk.rep_max == max_quantifier {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("+")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if tk.rep_min == 0 && tk.rep_max == max_quantifier {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("*")
|
2020-01-13 15:30:41 +03:00
|
|
|
} else {
|
2020-05-22 00:33:51 +03:00
|
|
|
if tk.rep_max == max_quantifier {
|
2020-01-25 21:12:23 +03:00
|
|
|
res.write("{${tk.rep_min},MAX}")
|
2020-01-13 15:30:41 +03:00
|
|
|
} else {
|
2020-01-25 21:12:23 +03:00
|
|
|
res.write("{${tk.rep_min},${tk.rep_max}}")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-01-25 21:12:23 +03:00
|
|
|
if tk.greedy == true {
|
2020-01-16 02:39:33 +03:00
|
|
|
res.write("?")
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
}
|
|
|
|
i++
|
|
|
|
}
|
2020-05-22 00:33:51 +03:00
|
|
|
if (re.flag & f_me) != 0 {
|
2020-01-14 04:45:08 +03:00
|
|
|
res.write("$")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-01-14 04:45:08 +03:00
|
|
|
return res.str()
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-06-08 00:04:23 +03:00
|
|
|
/*
|
|
|
|
|
|
|
|
Matching
|
|
|
|
|
|
|
|
*/
|
2020-04-23 06:16:10 +03:00
|
|
|
enum Match_state{
|
2020-04-23 02:16:16 +03:00
|
|
|
start = 0
|
|
|
|
stop
|
|
|
|
end
|
|
|
|
new_line
|
|
|
|
|
|
|
|
ist_load // load and execute instruction
|
|
|
|
ist_next // go to next instruction
|
|
|
|
ist_next_ks // go to next instruction without clenaning the state
|
|
|
|
ist_quant_p // match positive ,quantifier check
|
|
|
|
ist_quant_n // match negative, quantifier check
|
|
|
|
ist_quant_pg // match positive ,group quantifier check
|
|
|
|
ist_quant_ng // match negative ,group quantifier check
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-04-23 06:16:10 +03:00
|
|
|
fn state_str(s Match_state) string {
|
2020-01-13 15:30:41 +03:00
|
|
|
match s{
|
|
|
|
.start { return "start" }
|
|
|
|
.stop { return "stop" }
|
|
|
|
.end { return "end" }
|
2020-01-16 02:39:33 +03:00
|
|
|
.new_line { return "new line" }
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
.ist_load { return "ist_load" }
|
|
|
|
.ist_next { return "ist_next" }
|
|
|
|
.ist_next_ks { return "ist_next_ks" }
|
|
|
|
.ist_quant_p { return "ist_quant_p" }
|
|
|
|
.ist_quant_n { return "ist_quant_n" }
|
|
|
|
.ist_quant_pg { return "ist_quant_pg" }
|
|
|
|
.ist_quant_ng { return "ist_quant_ng" }
|
2020-04-23 02:16:16 +03:00
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
struct StateObj {
|
|
|
|
pub mut:
|
2020-12-03 21:33:53 +03:00
|
|
|
match_flag bool
|
2020-01-13 15:30:41 +03:00
|
|
|
match_index int = -1
|
|
|
|
match_first int = -1
|
|
|
|
}
|
|
|
|
|
2020-05-17 14:51:18 +03:00
|
|
|
pub fn (mut re RE) match_base(in_txt byteptr, in_txt_len int ) (int,int) {
|
2020-01-13 15:30:41 +03:00
|
|
|
// result status
|
2020-12-03 21:33:53 +03:00
|
|
|
mut result := no_match_found // function return
|
2020-01-13 15:30:41 +03:00
|
|
|
mut first_match := -1 //index of the first match
|
|
|
|
|
2020-12-03 21:33:53 +03:00
|
|
|
mut i := 0 // source string index
|
|
|
|
mut ch := rune(0) // examinated char
|
|
|
|
mut char_len := 0 // utf8 examinated char len
|
|
|
|
mut m_state := Match_state.start // start point for the matcher FSM
|
2020-12-05 03:51:48 +03:00
|
|
|
mut src_end := false
|
|
|
|
mut last_fnd_pc := -1
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-12-03 21:33:53 +03:00
|
|
|
mut pc := -1 // program counter
|
|
|
|
mut state := StateObj{} // actual state
|
|
|
|
mut ist := rune(0) // actual instruction
|
|
|
|
mut l_ist :=rune(0) // last matched instruction
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-12-03 21:33:53 +03:00
|
|
|
//mut group_stack := [-1].repeat(re.group_max)
|
|
|
|
//mut group_data := [-1].repeat(re.group_max)
|
|
|
|
mut group_stack := []int{len: re.group_max, init: -1}
|
|
|
|
mut group_data := []int{len: re.group_max, init: -1}
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-12-03 21:33:53 +03:00
|
|
|
mut group_index := -1 // group id used to know how many groups are open
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-12-03 21:33:53 +03:00
|
|
|
mut step_count := 0 // stats for debug
|
|
|
|
mut dbg_line := 0 // count debug line printed
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
re.reset()
|
|
|
|
|
|
|
|
if re.debug>0 {
|
|
|
|
// print header
|
2020-01-14 04:45:08 +03:00
|
|
|
mut h_buf := strings.new_builder(32)
|
|
|
|
h_buf.write("flags: ")
|
|
|
|
h_buf.write("${re.flag:8x}".replace(" ","0"))
|
|
|
|
h_buf.write("\n")
|
2020-04-25 23:42:48 +03:00
|
|
|
sss := h_buf.str()
|
|
|
|
re.log_func(sss)
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
for m_state != .end {
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
if pc >= 0 && pc < re.prog.len {
|
|
|
|
ist = re.prog[pc].ist
|
|
|
|
}else if pc >= re.prog.len {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("ERROR!! PC overflow!!")
|
2020-05-22 00:33:51 +03:00
|
|
|
return err_internal_error, i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
//******************************************
|
|
|
|
// DEBUG LOG
|
|
|
|
//******************************************
|
|
|
|
if re.debug>0 {
|
2020-12-03 21:33:53 +03:00
|
|
|
mut buf2 := strings.new_builder(re.cc.len + 128)
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-04-23 02:16:16 +03:00
|
|
|
// print all the instructions
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// end of the input text
|
|
|
|
if i >= in_txt_len {
|
2020-01-14 04:45:08 +03:00
|
|
|
buf2.write("# ${step_count:3d} END OF INPUT TEXT\n")
|
2020-04-25 23:42:48 +03:00
|
|
|
sss := buf2.str()
|
|
|
|
re.log_func(sss)
|
2020-01-13 15:30:41 +03:00
|
|
|
}else{
|
|
|
|
|
2020-01-16 02:39:33 +03:00
|
|
|
// print only the exe instruction
|
2020-01-13 15:30:41 +03:00
|
|
|
if (re.debug == 1 && m_state == .ist_load) ||
|
|
|
|
re.debug == 2
|
2020-04-23 02:16:16 +03:00
|
|
|
{
|
2020-05-22 00:33:51 +03:00
|
|
|
if ist == ist_prog_end {
|
2020-01-14 04:45:08 +03:00
|
|
|
buf2.write("# ${step_count:3d} PROG_END\n")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
else if ist == 0 || m_state in [.start,.ist_next,.stop] {
|
2020-01-14 04:45:08 +03:00
|
|
|
buf2.write("# ${step_count:3d} s: ${state_str(m_state):12s} PC: NA\n")
|
2020-01-13 15:30:41 +03:00
|
|
|
}else{
|
2020-01-16 02:39:33 +03:00
|
|
|
ch, char_len = re.get_charb(in_txt,i)
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-14 04:45:08 +03:00
|
|
|
buf2.write("# ${step_count:3d} s: ${state_str(m_state):12s} PC: ${pc:3d}=>")
|
|
|
|
buf2.write("${ist:8x}".replace(" ","0"))
|
|
|
|
buf2.write(" i,ch,len:[${i:3d},'${utf8_str(ch)}',${char_len}] f.m:[${first_match:3d},${state.match_index:3d}] ")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
if ist == ist_simple_char {
|
2020-01-16 02:39:33 +03:00
|
|
|
buf2.write("query_ch: [${re.prog[pc].ch:1c}]")
|
2020-01-13 15:30:41 +03:00
|
|
|
} else {
|
2020-05-22 00:33:51 +03:00
|
|
|
if ist == ist_bsls_char {
|
2020-01-16 02:39:33 +03:00
|
|
|
buf2.write("BSLS [\\${re.prog[pc].ch:1c}]")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_prog_end {
|
2020-01-14 04:45:08 +03:00
|
|
|
buf2.write("PROG_END")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_or_branch {
|
2020-01-14 04:45:08 +03:00
|
|
|
buf2.write("OR")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_char_class_pos {
|
2020-01-14 04:45:08 +03:00
|
|
|
buf2.write("CHAR_CLASS_POS[${re.get_char_class(pc)}]")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_char_class_neg {
|
2020-01-14 04:45:08 +03:00
|
|
|
buf2.write("CHAR_CLASS_NEG[${re.get_char_class(pc)}]")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_dot_char {
|
2020-01-14 04:45:08 +03:00
|
|
|
buf2.write("DOT_CHAR")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_group_start {
|
2020-01-14 04:45:08 +03:00
|
|
|
tmp_gi :=re.prog[pc].group_id
|
|
|
|
tmp_gr := re.prog[re.prog[pc].goto_pc].group_rep
|
|
|
|
buf2.write("GROUP_START #:${tmp_gi} rep:${tmp_gr} ")
|
2020-05-22 00:33:51 +03:00
|
|
|
} else if ist == ist_group_end {
|
2020-01-18 09:38:00 +03:00
|
|
|
buf2.write("GROUP_END #:${re.prog[pc].group_id} deep:${group_index}")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
}
|
2020-05-22 00:33:51 +03:00
|
|
|
if re.prog[pc].rep_max == max_quantifier {
|
2020-01-14 04:45:08 +03:00
|
|
|
buf2.write("{${re.prog[pc].rep_min},MAX}:${re.prog[pc].rep}")
|
2020-01-13 15:30:41 +03:00
|
|
|
} else {
|
2020-01-14 04:45:08 +03:00
|
|
|
buf2.write("{${re.prog[pc].rep_min},${re.prog[pc].rep_max}}:${re.prog[pc].rep}")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-01-16 02:39:33 +03:00
|
|
|
if re.prog[pc].greedy == true {
|
|
|
|
buf2.write("?")
|
|
|
|
}
|
2020-01-14 04:45:08 +03:00
|
|
|
buf2.write(" (#${group_index})\n")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-04-25 23:42:48 +03:00
|
|
|
sss2 := buf2.str()
|
|
|
|
re.log_func( sss2 )
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
}
|
|
|
|
step_count++
|
|
|
|
dbg_line++
|
|
|
|
}
|
|
|
|
//******************************************
|
2020-12-05 03:51:48 +03:00
|
|
|
/* if ist == ist_prog_end {
|
|
|
|
//println("HERE")
|
|
|
|
break
|
|
|
|
}
|
|
|
|
*/
|
2020-01-13 15:30:41 +03:00
|
|
|
// we're out of text, manage it
|
2020-01-16 02:39:33 +03:00
|
|
|
if i >= in_txt_len || m_state == .new_line {
|
2020-12-05 03:51:48 +03:00
|
|
|
src_end = true
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// manage groups
|
|
|
|
if group_index >= 0 && state.match_index >= 0 {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("End text with open groups!")
|
2020-01-13 15:30:41 +03:00
|
|
|
// close the groups
|
|
|
|
for group_index >= 0 {
|
|
|
|
tmp_pc := group_data[group_index]
|
|
|
|
re.prog[tmp_pc].group_rep++
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("Closing group $group_index {${re.prog[tmp_pc].rep_min},${re.prog[tmp_pc].rep_max}}:${re.prog[tmp_pc].group_rep}")
|
2020-05-17 14:51:18 +03:00
|
|
|
|
2020-01-28 22:34:11 +03:00
|
|
|
if re.prog[tmp_pc].group_rep >= re.prog[tmp_pc].rep_min && re.prog[tmp_pc].group_id >= 0{
|
2020-01-13 15:30:41 +03:00
|
|
|
start_i := group_stack[group_index]
|
|
|
|
group_stack[group_index]=-1
|
|
|
|
|
|
|
|
// save group results
|
|
|
|
g_index := re.prog[tmp_pc].group_id*2
|
|
|
|
if start_i >= 0 {
|
|
|
|
re.groups[g_index] = start_i
|
|
|
|
} else {
|
|
|
|
re.groups[g_index] = 0
|
|
|
|
}
|
|
|
|
re.groups[g_index+1] = i
|
2020-01-25 21:12:23 +03:00
|
|
|
|
|
|
|
// continuous save, save until we have space
|
|
|
|
if re.group_csave_index > 0 {
|
|
|
|
// check if we have space to save the record
|
|
|
|
if (re.group_csave_index + 3) < re.group_csave.len {
|
|
|
|
// incrment counter
|
|
|
|
re.group_csave[0]++
|
2020-04-23 02:16:16 +03:00
|
|
|
// save the record
|
2020-01-28 22:34:11 +03:00
|
|
|
re.group_csave[re.group_csave_index++] = g_index >> 1 // group id
|
2020-01-25 21:12:23 +03:00
|
|
|
re.group_csave[re.group_csave_index++] = re.groups[g_index] // start
|
|
|
|
re.group_csave[re.group_csave_index++] = re.groups[g_index+1] // end
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
group_index--
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-12-05 03:51:48 +03:00
|
|
|
if pc == -1 {
|
|
|
|
pc = last_fnd_pc
|
|
|
|
}
|
|
|
|
//println("Finished text!!")
|
|
|
|
//println("Instruction: ${ist:08x} pc: $pc")
|
|
|
|
//println("min_rep: ${re.prog[pc].rep_min} max_rep: ${re.prog[pc].rep_max} rep: ${re.prog[pc].rep}")
|
|
|
|
|
|
|
|
// program end
|
|
|
|
if ist == ist_prog_end {
|
|
|
|
//println("Program end on end of text!")
|
|
|
|
return first_match,i
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-12-05 03:51:48 +03:00
|
|
|
// if we go out of text and we are the last instruction .* check
|
|
|
|
if (re.prog[pc+1].ist == ist_prog_end) &&
|
|
|
|
(re.prog[pc].rep >= re.prog[pc].rep_min && re.prog[pc].rep <= re.prog[pc].rep_max) {
|
|
|
|
//println("Ok .* rep match!")
|
|
|
|
return first_match,i
|
|
|
|
}
|
|
|
|
|
|
|
|
//m_state = .end
|
|
|
|
//break
|
|
|
|
return no_match_found,0
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// starting and init
|
|
|
|
if m_state == .start {
|
|
|
|
pc = -1
|
2020-12-03 21:33:53 +03:00
|
|
|
i = 0
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-01-16 02:39:33 +03:00
|
|
|
// ist_next, next instruction reseting its state
|
2020-01-13 15:30:41 +03:00
|
|
|
if m_state == .ist_next {
|
|
|
|
pc = pc + 1
|
|
|
|
re.prog[pc].reset()
|
|
|
|
// check if we are in the program bounds
|
|
|
|
if pc < 0 || pc > re.prog.len {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("ERROR!! PC overflow!!")
|
2020-05-22 00:33:51 +03:00
|
|
|
return err_internal_error, i
|
2020-04-23 02:16:16 +03:00
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_load
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-01-16 02:39:33 +03:00
|
|
|
// ist_next_ks, next instruction keeping its state
|
2020-01-13 15:30:41 +03:00
|
|
|
if m_state == .ist_next_ks {
|
|
|
|
pc = pc + 1
|
|
|
|
// check if we are in the program bounds
|
|
|
|
if pc < 0 || pc > re.prog.len {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("ERROR!! PC overflow!!")
|
2020-05-22 00:33:51 +03:00
|
|
|
return err_internal_error, i
|
2020-04-23 02:16:16 +03:00
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_load
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// load the char
|
2020-01-16 02:39:33 +03:00
|
|
|
ch, char_len = re.get_charb(in_txt,i)
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
// check new line if flag f_nl enabled
|
|
|
|
if (re.flag & f_nl) != 0 && char_len == 1 && byte(ch) in new_line_list {
|
2020-01-16 02:39:33 +03:00
|
|
|
m_state = .new_line
|
|
|
|
continue
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-04-23 02:16:16 +03:00
|
|
|
// check if stop
|
2020-01-13 15:30:41 +03:00
|
|
|
if m_state == .stop {
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-31 04:29:54 +03:00
|
|
|
// we are in search mode, don't exit until the end
|
2020-12-05 03:51:48 +03:00
|
|
|
if ((re.flag & f_src) != 0) && (ist != ist_prog_end) {
|
|
|
|
last_fnd_pc = pc
|
2020-01-31 04:29:54 +03:00
|
|
|
pc = -1
|
|
|
|
i += char_len
|
|
|
|
m_state = .ist_next
|
|
|
|
re.reset_src()
|
|
|
|
state.match_index = -1
|
|
|
|
first_match = -1
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// if we are in restore state ,do it and restart
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("re.state_stack_index ${re.state_stack_index}")
|
2020-01-18 09:38:00 +03:00
|
|
|
if re.state_stack_index >=0 && re.state_stack[re.state_stack_index].pc >= 0 {
|
2020-01-13 15:30:41 +03:00
|
|
|
i = re.state_stack[re.state_stack_index].i
|
|
|
|
pc = re.state_stack[re.state_stack_index].pc
|
|
|
|
state.match_index = re.state_stack[re.state_stack_index].mi
|
|
|
|
group_index = re.state_stack[re.state_stack_index].group_stack_index
|
2020-01-18 09:38:00 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_load
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
if ist == ist_prog_end {
|
2020-01-13 15:30:41 +03:00
|
|
|
return first_match,i
|
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// exit on no match
|
|
|
|
return result,0
|
|
|
|
}
|
|
|
|
|
|
|
|
// ist_load
|
|
|
|
if m_state == .ist_load {
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// program end
|
2020-05-22 00:33:51 +03:00
|
|
|
if ist == ist_prog_end {
|
2020-01-13 15:30:41 +03:00
|
|
|
// if we are in match exit well
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
if group_index >= 0 && state.match_index >= 0 {
|
|
|
|
group_index = -1
|
|
|
|
}
|
2020-01-18 09:38:00 +03:00
|
|
|
|
|
|
|
// we have a DOT MATCH on going
|
2020-05-22 00:33:51 +03:00
|
|
|
//println("ist_prog_end l_ist: ${l_ist:08x}", l_ist)
|
|
|
|
if re.state_stack_index>=0 && l_ist == ist_dot_char {
|
2020-12-05 03:51:48 +03:00
|
|
|
i = in_txt_len // dario
|
2020-01-18 09:38:00 +03:00
|
|
|
m_state = .stop
|
|
|
|
continue
|
2020-12-05 03:51:48 +03:00
|
|
|
}
|
2020-01-18 09:38:00 +03:00
|
|
|
|
|
|
|
re.state_stack_index = -1
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .stop
|
|
|
|
continue
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// check GROUP start, no quantifier is checkd for this token!!
|
2020-05-22 00:33:51 +03:00
|
|
|
else if ist == ist_group_start {
|
2020-01-13 15:30:41 +03:00
|
|
|
group_index++
|
2020-05-22 00:33:51 +03:00
|
|
|
group_data[group_index] = re.prog[pc].goto_pc // save where is ist_group_end, we will use it for escape
|
2020-01-13 15:30:41 +03:00
|
|
|
group_stack[group_index]=i // index where we start to manage
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("group_index $group_index rep ${re.prog[re.prog[pc].goto_pc].group_rep}")
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// check GROUP end
|
2020-05-22 00:33:51 +03:00
|
|
|
else if ist == ist_group_end {
|
2020-01-13 15:30:41 +03:00
|
|
|
// we are in matching streak
|
|
|
|
if state.match_index >= 0 {
|
|
|
|
// restore txt index stack and save the group data
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("g.id: ${re.prog[pc].group_id} group_index: ${group_index}")
|
2020-01-28 22:34:11 +03:00
|
|
|
if group_index >= 0 && re.prog[pc].group_id >= 0 {
|
2020-01-13 15:30:41 +03:00
|
|
|
start_i := group_stack[group_index]
|
2020-01-18 09:38:00 +03:00
|
|
|
//group_stack[group_index]=-1
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// save group results
|
|
|
|
g_index := re.prog[pc].group_id*2
|
|
|
|
if start_i >= 0 {
|
|
|
|
re.groups[g_index] = start_i
|
|
|
|
} else {
|
|
|
|
re.groups[g_index] = 0
|
|
|
|
}
|
|
|
|
re.groups[g_index+1] = i
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("GROUP ${re.prog[pc].group_id} END [${re.groups[g_index]}, ${re.groups[g_index+1]}]")
|
2020-01-25 21:12:23 +03:00
|
|
|
|
|
|
|
// continuous save, save until we have space
|
|
|
|
if re.group_csave_index > 0 {
|
|
|
|
// check if we have space to save the record
|
|
|
|
if (re.group_csave_index + 3) < re.group_csave.len {
|
|
|
|
// incrment counter
|
|
|
|
re.group_csave[0]++
|
2020-04-23 02:16:16 +03:00
|
|
|
// save the record
|
2020-01-28 22:34:11 +03:00
|
|
|
re.group_csave[re.group_csave_index++] = g_index >> 1 // group id
|
2020-01-25 21:12:23 +03:00
|
|
|
re.group_csave[re.group_csave_index++] = re.groups[g_index] // start
|
|
|
|
re.group_csave[re.group_csave_index++] = re.groups[g_index+1] // end
|
|
|
|
}
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[pc].group_rep++ // increase repetitions
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("GROUP $group_index END ${re.prog[pc].group_rep}")
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_quant_pg
|
|
|
|
continue
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
m_state = .ist_quant_ng
|
2020-04-23 02:16:16 +03:00
|
|
|
continue
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// check OR
|
2020-05-22 00:33:51 +03:00
|
|
|
else if ist == ist_or_branch {
|
2020-01-13 15:30:41 +03:00
|
|
|
if state.match_index >= 0 {
|
|
|
|
pc = re.prog[pc].rep_max
|
2020-05-22 00:33:51 +03:00
|
|
|
//println("ist_or_branch True pc: $pc")
|
2020-01-13 15:30:41 +03:00
|
|
|
}else{
|
|
|
|
pc = re.prog[pc].rep_min
|
2020-05-22 00:33:51 +03:00
|
|
|
//println("ist_or_branch False pc: $pc")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
re.prog[pc].reset()
|
2020-11-26 02:28:41 +03:00
|
|
|
m_state = .ist_load
|
2020-01-13 15:30:41 +03:00
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
// check ist_dot_char
|
|
|
|
else if ist == ist_dot_char {
|
|
|
|
//println("ist_dot_char rep: ${re.prog[pc].rep}")
|
2020-01-13 15:30:41 +03:00
|
|
|
state.match_flag = true
|
2020-05-22 00:33:51 +03:00
|
|
|
l_ist = u32(ist_dot_char)
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
if first_match < 0 {
|
|
|
|
first_match = i
|
|
|
|
}
|
|
|
|
state.match_index = i
|
2020-12-05 03:51:48 +03:00
|
|
|
re.prog[pc].rep++ // increase repetitions
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-01-18 09:38:00 +03:00
|
|
|
//if re.prog[pc].rep >= re.prog[pc].rep_min && re.prog[pc].rep <= re.prog[pc].rep_max {
|
|
|
|
if re.prog[pc].rep >= 0 && re.prog[pc].rep <= re.prog[pc].rep_max {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("DOT CHAR save state : ${re.state_stack_index}")
|
2020-01-13 15:30:41 +03:00
|
|
|
// save the state
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-18 09:38:00 +03:00
|
|
|
// manage first dot char
|
|
|
|
if re.state_stack_index < 0 {
|
|
|
|
re.state_stack_index++
|
|
|
|
}
|
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
re.state_stack[re.state_stack_index].pc = pc
|
|
|
|
re.state_stack[re.state_stack_index].mi = state.match_index
|
|
|
|
re.state_stack[re.state_stack_index].group_stack_index = group_index
|
2020-01-18 09:38:00 +03:00
|
|
|
} else {
|
|
|
|
re.state_stack[re.state_stack_index].pc = -1
|
|
|
|
re.state_stack[re.state_stack_index].mi = -1
|
|
|
|
re.state_stack[re.state_stack_index].group_stack_index = -1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
if re.prog[pc].rep >= 1 && re.state_stack_index >= 0 {
|
|
|
|
re.state_stack[re.state_stack_index].i = i + char_len
|
2020-04-23 02:16:16 +03:00
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-12-05 03:51:48 +03:00
|
|
|
//i += char_len // next char
|
|
|
|
/*
|
2020-01-13 15:30:41 +03:00
|
|
|
// manage * and {0,} quantifier
|
2020-12-05 03:51:48 +03:00
|
|
|
if re.prog[pc].rep_max == max_quantifier {
|
|
|
|
//println("manage .*")
|
|
|
|
m_state = .ist_load
|
|
|
|
continue
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-12-05 03:51:48 +03:00
|
|
|
*/
|
2020-01-18 09:38:00 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
// char class IST
|
2020-05-22 00:33:51 +03:00
|
|
|
else if ist == ist_char_class_pos || ist == ist_char_class_neg {
|
2020-01-13 15:30:41 +03:00
|
|
|
state.match_flag = false
|
|
|
|
mut cc_neg := false
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
if ist == ist_char_class_neg {
|
2020-01-13 15:30:41 +03:00
|
|
|
cc_neg = true
|
|
|
|
}
|
|
|
|
mut cc_res := re.check_char_class(pc,ch)
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
if cc_neg {
|
|
|
|
cc_res = !cc_res
|
|
|
|
}
|
|
|
|
|
|
|
|
if cc_res {
|
|
|
|
state.match_flag = true
|
2020-05-22 00:33:51 +03:00
|
|
|
l_ist = u32(ist_char_class_pos)
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
if first_match < 0 {
|
|
|
|
first_match = i
|
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
state.match_index = i
|
|
|
|
|
|
|
|
re.prog[pc].rep++ // increase repetitions
|
|
|
|
i += char_len // next char
|
|
|
|
m_state = .ist_quant_p
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
m_state = .ist_quant_n
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// check bsls
|
2020-05-22 00:33:51 +03:00
|
|
|
else if ist == ist_bsls_char {
|
2020-01-13 15:30:41 +03:00
|
|
|
state.match_flag = false
|
|
|
|
tmp_res := re.prog[pc].validator(byte(ch))
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("BSLS in_ch: ${ch:c} res: $tmp_res")
|
2020-01-13 15:30:41 +03:00
|
|
|
if tmp_res {
|
|
|
|
state.match_flag = true
|
2020-05-22 00:33:51 +03:00
|
|
|
l_ist = u32(ist_bsls_char)
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
if first_match < 0 {
|
|
|
|
first_match = i
|
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
state.match_index = i
|
|
|
|
|
|
|
|
re.prog[pc].rep++ // increase repetitions
|
|
|
|
i += char_len // next char
|
|
|
|
m_state = .ist_quant_p
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
m_state = .ist_quant_n
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// simple char IST
|
2020-05-22 00:33:51 +03:00
|
|
|
else if ist == ist_simple_char {
|
|
|
|
//println("ist_simple_char")
|
2020-01-13 15:30:41 +03:00
|
|
|
state.match_flag = false
|
|
|
|
|
2020-01-16 02:39:33 +03:00
|
|
|
if re.prog[pc].ch == ch
|
2020-01-13 15:30:41 +03:00
|
|
|
{
|
|
|
|
state.match_flag = true
|
2020-05-22 00:33:51 +03:00
|
|
|
l_ist = ist_simple_char
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
if first_match < 0 {
|
|
|
|
first_match = i
|
|
|
|
}
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("state.match_index: ${state.match_index}")
|
2020-01-13 15:30:41 +03:00
|
|
|
state.match_index = i
|
|
|
|
|
|
|
|
re.prog[pc].rep++ // increase repetitions
|
|
|
|
i += char_len // next char
|
|
|
|
m_state = .ist_quant_p
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
m_state = .ist_quant_n
|
|
|
|
continue
|
2020-04-23 02:16:16 +03:00
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
/* UNREACHABLE */
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("PANIC2!! state: $m_state")
|
2020-05-22 00:33:51 +03:00
|
|
|
return err_internal_error, i
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
/***********************************
|
2020-04-23 02:16:16 +03:00
|
|
|
* Quantifier management
|
2020-01-13 15:30:41 +03:00
|
|
|
***********************************/
|
2020-12-03 21:33:53 +03:00
|
|
|
// ist_quant_ng => quantifier negative test on group
|
2020-01-13 15:30:41 +03:00
|
|
|
if m_state == .ist_quant_ng {
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// we are finished here
|
|
|
|
if group_index < 0 {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("Early stop!")
|
2020-05-22 00:33:51 +03:00
|
|
|
result = no_match_found
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .stop
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp_pc := group_data[group_index] // PC to the end of the group token
|
2020-04-23 02:16:16 +03:00
|
|
|
rep := re.prog[tmp_pc].group_rep // use a temp variable
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[tmp_pc].group_rep = 0 // clear the repetitions
|
|
|
|
|
2020-05-16 18:11:13 +03:00
|
|
|
//println(".ist_quant_ng group_pc_end: $tmp_pc rep: $rep")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
if rep >= re.prog[tmp_pc].rep_min {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("ist_quant_ng GROUP CLOSED OK group_index: $group_index")
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
i = group_stack[group_index]
|
|
|
|
pc = tmp_pc
|
|
|
|
group_index--
|
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
else if re.prog[tmp_pc].next_is_or {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("ist_quant_ng OR Negative branch")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
i = group_stack[group_index]
|
|
|
|
pc = re.prog[tmp_pc+1].rep_min -1
|
|
|
|
group_index--
|
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
else if rep>0 && rep < re.prog[tmp_pc].rep_min {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("ist_quant_ng UNDER THE MINIMUM g.i: $group_index")
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// check if we are inside a group, if yes exit from the nested groups
|
|
|
|
if group_index > 0{
|
|
|
|
group_index--
|
|
|
|
pc = tmp_pc
|
|
|
|
m_state = .ist_quant_ng //.ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
if group_index == 0 {
|
|
|
|
group_index--
|
|
|
|
pc = tmp_pc // TEST
|
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
result = no_match_found
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .stop
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
else if rep==0 && rep < re.prog[tmp_pc].rep_min {
|
2020-05-22 18:36:09 +03:00
|
|
|
//println("ist_quant_ng c_zero UNDER THE MINIMUM g.i: $group_index")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
if group_index > 0{
|
|
|
|
group_index--
|
|
|
|
pc = tmp_pc
|
|
|
|
m_state = .ist_quant_ng //.ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
result = no_match_found
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .stop
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("DO NOT STAY HERE!! {${re.prog[tmp_pc].rep_min},${re.prog[tmp_pc].rep_max}}:$rep")
|
2020-01-13 15:30:41 +03:00
|
|
|
/* UNREACHABLE */
|
2020-05-22 00:33:51 +03:00
|
|
|
return err_internal_error, i
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
}
|
2020-12-03 21:33:53 +03:00
|
|
|
// ist_quant_pg => quantifier positive test on group
|
2020-01-13 15:30:41 +03:00
|
|
|
else if m_state == .ist_quant_pg {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println(".ist_quant_pg")
|
2020-01-13 15:30:41 +03:00
|
|
|
mut tmp_pc := pc
|
|
|
|
if group_index >= 0 {
|
2020-04-23 02:16:16 +03:00
|
|
|
tmp_pc = group_data[group_index]
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
rep := re.prog[tmp_pc].group_rep
|
|
|
|
|
|
|
|
if rep < re.prog[tmp_pc].rep_min {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("ist_quant_pg UNDER RANGE")
|
2020-04-23 02:16:16 +03:00
|
|
|
pc = re.prog[tmp_pc].goto_pc
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
else if rep == re.prog[tmp_pc].rep_max {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("ist_quant_pg MAX RANGE")
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[tmp_pc].group_rep = 0 // clear the repetitions
|
|
|
|
group_index--
|
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
else if rep >= re.prog[tmp_pc].rep_min {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("ist_quant_pg IN RANGE group_index:$group_index")
|
2020-01-16 02:39:33 +03:00
|
|
|
|
|
|
|
// check greedy flag, if true exit on minimum
|
|
|
|
if re.prog[tmp_pc].greedy == true {
|
|
|
|
re.prog[tmp_pc].group_rep = 0 // clear the repetitions
|
|
|
|
group_index--
|
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
pc = re.prog[tmp_pc].goto_pc - 1
|
|
|
|
group_index--
|
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
/* UNREACHABLE */
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("PANIC3!! state: $m_state")
|
2020-05-22 00:33:51 +03:00
|
|
|
return err_internal_error, i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-12-03 21:33:53 +03:00
|
|
|
// ist_quant_n => quantifier negative test on token
|
2020-01-13 15:30:41 +03:00
|
|
|
else if m_state == .ist_quant_n {
|
|
|
|
rep := re.prog[pc].rep
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("Here!! PC $pc is_next_or: ${re.prog[pc].next_is_or}")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// zero quantifier * or ?
|
|
|
|
if rep == 0 && re.prog[pc].rep_min == 0 {
|
2020-05-22 18:36:09 +03:00
|
|
|
//println("ist_quant_n c_zero RANGE MIN")
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next // go to next ist
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
// match + or *
|
|
|
|
else if rep >= re.prog[pc].rep_min {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("ist_quant_n MATCH RANGE")
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// check the OR if present
|
|
|
|
if re.prog[pc].next_is_or {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("OR present on failing")
|
2020-01-13 15:30:41 +03:00
|
|
|
state.match_index = -1
|
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// we are in a group manage no match from here
|
|
|
|
if group_index >= 0 {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("ist_quant_n FAILED insied a GROUP group_index:$group_index")
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_quant_ng
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// no other options
|
2020-05-22 00:33:51 +03:00
|
|
|
//println("ist_quant_n no_match_found")
|
|
|
|
result = no_match_found
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .stop
|
|
|
|
continue
|
2020-05-22 00:33:51 +03:00
|
|
|
//return no_match_found, 0
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-12-03 21:33:53 +03:00
|
|
|
// ist_quant_p => quantifier positive test on token
|
2020-01-13 15:30:41 +03:00
|
|
|
else if m_state == .ist_quant_p {
|
|
|
|
// exit on first match
|
2020-05-22 00:33:51 +03:00
|
|
|
if (re.flag & f_efm) != 0 {
|
2020-01-13 15:30:41 +03:00
|
|
|
return i,i+1
|
|
|
|
}
|
|
|
|
|
|
|
|
rep := re.prog[pc].rep
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// under range
|
|
|
|
if rep > 0 && rep < re.prog[pc].rep_min {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("ist_quant_p UNDER RANGE")
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_load // continue the loop
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// range ok, continue loop
|
|
|
|
else if rep >= re.prog[pc].rep_min && rep < re.prog[pc].rep_max {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("ist_quant_p IN RANGE")
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-16 02:39:33 +03:00
|
|
|
// check greedy flag, if true exit on minimum
|
|
|
|
if re.prog[pc].greedy == true {
|
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_load
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// max reached
|
|
|
|
else if rep == re.prog[pc].rep_max {
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("ist_quant_p MAX RANGE")
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
}
|
|
|
|
/* UNREACHABLE */
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("PANIC4!! state: $m_state")
|
2020-05-22 00:33:51 +03:00
|
|
|
return err_internal_error, i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-12-05 03:51:48 +03:00
|
|
|
//println("Check end of text!")
|
2020-01-13 15:30:41 +03:00
|
|
|
// Check the results
|
|
|
|
if state.match_index >= 0 {
|
|
|
|
if group_index < 0 {
|
2020-12-05 03:51:48 +03:00
|
|
|
|
|
|
|
if re.prog[pc].ist == ist_prog_end {
|
|
|
|
//println("program ended!!")
|
|
|
|
|
|
|
|
if (re.flag & f_src) != 0 {
|
|
|
|
//println("find return")
|
|
|
|
return first_match, i
|
|
|
|
} else {
|
|
|
|
return 0, i
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
//println("No Group here, natural end [$first_match,$i] state: ${state_str(m_state)} ist: $ist pgr_end: $re.prog.len")
|
|
|
|
|
|
|
|
if re.prog[pc+1].ist == ist_prog_end || re.prog[pc].ist == ist_prog_end{
|
|
|
|
rep := re.prog[pc].rep
|
|
|
|
//println("rep: $rep re.prog[pc].rep_min: ${re.prog[pc].rep_min} re.prog[pc].rep_max: ${re.prog[pc].rep_max}")
|
|
|
|
if rep >= re.prog[pc].rep_min && rep <= re.prog[pc].rep_max {
|
|
|
|
return first_match, i
|
|
|
|
}
|
|
|
|
//println("Program not finished! ")
|
|
|
|
return no_match_found, 0
|
|
|
|
}
|
|
|
|
if src_end {
|
|
|
|
//println("program end")
|
|
|
|
return first_match, i
|
|
|
|
}
|
|
|
|
//print("No match found!!")
|
|
|
|
return no_match_found, 0
|
|
|
|
|
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
} else {
|
2020-12-05 03:51:48 +03:00
|
|
|
//println("Group match! OK")
|
|
|
|
//println("first_match: $first_match, i: $i")
|
|
|
|
|
2020-05-16 18:11:13 +03:00
|
|
|
//println("Skip last group")
|
2020-12-05 03:51:48 +03:00
|
|
|
return first_match,i
|
|
|
|
//return first_match,group_stack[group_index--]
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
}
|
2020-05-22 00:33:51 +03:00
|
|
|
//println("no_match_found, natural end")
|
|
|
|
return no_match_found, 0
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-06-08 00:04:23 +03:00
|
|
|
/*
|
|
|
|
|
|
|
|
Public functions
|
|
|
|
|
|
|
|
*/
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
//
|
|
|
|
// Inits
|
|
|
|
//
|
|
|
|
|
|
|
|
// regex create a regex object from the query string
|
2020-08-08 09:04:12 +03:00
|
|
|
[deprecated]
|
2020-01-13 15:30:41 +03:00
|
|
|
pub fn regex(in_query string) (RE,int,int){
|
|
|
|
mut re := RE{}
|
|
|
|
re.prog = [Token{}].repeat(in_query.len+1)
|
|
|
|
re.cc = [CharClass{}].repeat(in_query.len+1)
|
|
|
|
re.group_max_nested = 8
|
|
|
|
|
|
|
|
re_err,err_pos := re.compile(in_query)
|
|
|
|
return re, re_err, err_pos
|
|
|
|
}
|
|
|
|
|
2020-04-25 23:42:48 +03:00
|
|
|
// new_regex create a RE of small size, usually sufficient for ordinary use
|
2020-08-08 09:04:12 +03:00
|
|
|
[deprecated]
|
2020-01-13 15:30:41 +03:00
|
|
|
pub fn new_regex() RE {
|
2020-08-08 09:04:12 +03:00
|
|
|
return impl_new_regex_by_size(1)
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-04-25 23:42:48 +03:00
|
|
|
// new_regex_by_size create a RE of large size, mult specify the scale factor of the memory that will be allocated
|
2020-08-08 09:04:12 +03:00
|
|
|
[deprecated]
|
2020-01-13 15:30:41 +03:00
|
|
|
pub fn new_regex_by_size(mult int) RE {
|
2020-08-08 09:04:12 +03:00
|
|
|
return impl_new_regex_by_size(mult)
|
2020-08-27 07:46:18 +03:00
|
|
|
}
|
2020-08-08 09:04:12 +03:00
|
|
|
fn impl_new_regex_by_size(mult int) RE {
|
2020-01-13 15:30:41 +03:00
|
|
|
mut re := RE{}
|
2020-05-22 00:33:51 +03:00
|
|
|
re.prog = [Token{}].repeat(max_code_len*mult) // max program length, default 256 istructions
|
|
|
|
re.cc = [CharClass{}].repeat(max_code_len*mult) // char class list
|
2020-01-13 15:30:41 +03:00
|
|
|
re.group_max_nested = 3*mult // max nested group
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
return re
|
|
|
|
}
|
|
|
|
|
|
|
|
//
|
|
|
|
// Matchers
|
|
|
|
//
|
|
|
|
|
2020-05-17 14:51:18 +03:00
|
|
|
pub fn (mut re RE) match_string(in_txt string) (int,int) {
|
2020-12-05 03:51:48 +03:00
|
|
|
|
|
|
|
start, mut end := re.match_base(in_txt.str, in_txt.len + 1)
|
|
|
|
if end > in_txt.len {
|
|
|
|
end = in_txt.len
|
|
|
|
}
|
|
|
|
|
2020-04-23 02:16:16 +03:00
|
|
|
if start >= 0 && end > start {
|
2020-05-22 00:33:51 +03:00
|
|
|
if (re.flag & f_ms) != 0 && start > 0 {
|
|
|
|
return no_match_found, 0
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-05-22 00:33:51 +03:00
|
|
|
if (re.flag & f_me) != 0 && end < in_txt.len {
|
|
|
|
if in_txt[end] in new_line_list {
|
2020-01-25 21:12:23 +03:00
|
|
|
return start, end
|
|
|
|
}
|
2020-05-22 00:33:51 +03:00
|
|
|
return no_match_found, 0
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
return start, end
|
|
|
|
}
|
|
|
|
return start, end
|
|
|
|
}
|
|
|
|
|
|
|
|
//
|
|
|
|
// Finders
|
|
|
|
//
|
|
|
|
|
|
|
|
// find try to find the first match in the input string
|
2020-05-17 14:51:18 +03:00
|
|
|
pub fn (mut re RE) find(in_txt string) (int,int) {
|
2020-01-13 15:30:41 +03:00
|
|
|
old_flag := re.flag
|
2020-12-05 03:51:48 +03:00
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
re.flag |= f_src // enable search mode
|
2020-12-05 03:51:48 +03:00
|
|
|
start, mut end := re.match_base(in_txt.str, in_txt.len + 1)
|
|
|
|
//print("Find [$start,$end] '${in_txt[start..end]}'")
|
|
|
|
if end > in_txt.len {
|
|
|
|
end = in_txt.len
|
|
|
|
}
|
2020-01-31 04:29:54 +03:00
|
|
|
re.flag = old_flag
|
2020-12-05 03:51:48 +03:00
|
|
|
|
2020-01-31 04:29:54 +03:00
|
|
|
if start >= 0 && end > start {
|
2020-12-03 21:33:53 +03:00
|
|
|
return start, end
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-05-22 00:33:51 +03:00
|
|
|
return no_match_found, 0
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-01-14 04:45:08 +03:00
|
|
|
|
|
|
|
// find all the non overlapping occurrences of the match pattern
|
2020-05-17 14:51:18 +03:00
|
|
|
pub fn (mut re RE) find_all(in_txt string) []int {
|
2020-01-14 04:45:08 +03:00
|
|
|
mut i := 0
|
2020-04-26 14:49:31 +03:00
|
|
|
mut res := []int{}
|
2020-01-14 04:45:08 +03:00
|
|
|
mut ls := -1
|
|
|
|
for i < in_txt.len {
|
|
|
|
s,e := re.find(in_txt[i..])
|
|
|
|
if s >= 0 && e > s && i+s > ls {
|
|
|
|
//println("find match in: ${i+s},${i+e} [${in_txt[i+s..i+e]}] ls:$ls")
|
|
|
|
res << i+s
|
|
|
|
res << i+e
|
|
|
|
ls = i+s
|
|
|
|
i = i+e
|
|
|
|
continue
|
|
|
|
} else {
|
|
|
|
i++
|
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-14 04:45:08 +03:00
|
|
|
}
|
|
|
|
return res
|
|
|
|
}
|
|
|
|
|
|
|
|
// replace return a string where the matches are replaced with the replace string
|
2020-05-17 14:51:18 +03:00
|
|
|
pub fn (mut re RE) replace(in_txt string, repl string) string {
|
2020-01-14 04:45:08 +03:00
|
|
|
pos := re.find_all(in_txt)
|
|
|
|
if pos.len > 0 {
|
|
|
|
mut res := ""
|
|
|
|
mut i := 0
|
|
|
|
|
|
|
|
mut s1 := 0
|
|
|
|
mut e1 := in_txt.len
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-14 04:45:08 +03:00
|
|
|
for i < pos.len {
|
|
|
|
e1 = pos[i]
|
|
|
|
res += in_txt[s1..e1] + repl
|
|
|
|
s1 = pos[i+1]
|
|
|
|
i += 2
|
|
|
|
}
|
|
|
|
|
|
|
|
res += in_txt[s1..]
|
|
|
|
return res
|
|
|
|
}
|
|
|
|
return in_txt
|
|
|
|
}
|
2020-12-06 00:24:08 +03:00
|
|
|
|
|
|
|
/*
|
|
|
|
|
|
|
|
Utilities
|
|
|
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
pub
|
|
|
|
struct Re_group {
|
|
|
|
pub:
|
|
|
|
start int = -1
|
|
|
|
end int = -1
|
|
|
|
}
|
|
|
|
|
|
|
|
// get_group_list return a list of Re_group for the found groups
|
|
|
|
pub fn (re RE) get_group_list() []Re_group {
|
|
|
|
mut res := []Re_group{len: re.groups.len >> 1}
|
|
|
|
mut gi := 0
|
|
|
|
//println("len: ${re.groups.len} groups: ${re.groups}")
|
|
|
|
for gi < re.groups.len {
|
|
|
|
if re.groups[gi] >= 0 {
|
|
|
|
//println("#${gi/2} start: ${re.groups[gi]} end: ${re.groups[gi + 1]} ")
|
|
|
|
tmp := Re_group{ start: re.groups[gi], end: re.groups[gi + 1]}
|
|
|
|
//println(tmp)
|
|
|
|
res[gi >> 1] = tmp
|
|
|
|
}
|
|
|
|
gi += 2
|
|
|
|
}
|
|
|
|
return res
|
|
|
|
}
|
|
|
|
|