2020-06-08 00:04:23 +03:00
|
|
|
/*
|
2020-12-19 02:32:57 +03:00
|
|
|
regex 1.0 alpha
|
2020-06-08 00:04:23 +03:00
|
|
|
|
2021-01-18 15:20:06 +03:00
|
|
|
Copyright (c) 2019-2021 Dario Deledda. All rights reserved.
|
2020-06-08 00:04:23 +03:00
|
|
|
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
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
import strings
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
pub const (
|
|
|
|
v_regex_version = '1.0 alpha' // regex module version
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2021-05-08 13:32:29 +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
|
2021-05-08 13:32:29 +03:00
|
|
|
spaces = [` `, `\t`, `\n`, `\r`, `\v`, `\f`]
|
2020-01-13 15:30:41 +03:00
|
|
|
// new line chars for now only '\n'
|
2021-05-08 13:32:29 +03:00
|
|
|
new_line_list = [`\n`, `\r`]
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// Results
|
2021-05-08 13:32:29 +03:00
|
|
|
no_match_found = -1
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// Errors
|
2021-05-08 13:32:29 +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
|
|
|
)
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
const (
|
2020-01-13 15:30:41 +03:00
|
|
|
//*************************************
|
|
|
|
// regex program instructions
|
|
|
|
//*************************************
|
2021-05-08 13:32:29 +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
|
2021-05-08 13:32:29 +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
|
2021-05-08 13:32:29 +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
|
2021-05-08 13:32:29 +03:00
|
|
|
ist_bsls_char = 0x90000000 // backslash char
|
2020-01-13 15:30:41 +03:00
|
|
|
// OR | 10 010Y xx xxxxxxxx
|
2021-05-08 13:32:29 +03:00
|
|
|
ist_or_branch = 0x91000000 // OR case
|
2020-01-13 15:30:41 +03:00
|
|
|
// groups 10 010Y xx xxxxxxxx
|
2021-05-08 13:32:29 +03:00
|
|
|
ist_group_start = 0x92000000 // group start (
|
|
|
|
ist_group_end = 0x94000000 // group end )
|
2020-01-13 15:30:41 +03:00
|
|
|
// control instructions
|
2021-05-08 13:32:29 +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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
return ((0xe5000000 >> ((b >> 3) & 0x1e)) & 3) + 1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// get_char get a char from position i and return an u32 with the unicode code
|
2021-05-08 13:32:29 +03:00
|
|
|
[direct_array_access; inline]
|
|
|
|
fn (re RE) get_char(in_txt string, i int) (u32, int) {
|
|
|
|
ini := unsafe { in_txt.str[i] }
|
2020-01-13 15:30:41 +03:00
|
|
|
// ascii 8 bit
|
2021-05-08 13:32:29 +03:00
|
|
|
if (re.flag & regex.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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
ch = (ch << 8) | unsafe { in_txt.str[i + tmp] }
|
2020-01-13 15:30:41 +03:00
|
|
|
tmp++
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
return ch, char_len
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// get_charb get a char from position i and return an u32 with the unicode code
|
2021-05-08 13:32:29 +03:00
|
|
|
[direct_array_access; inline]
|
|
|
|
fn (re RE) get_charb(in_txt &byte, i int) (u32, int) {
|
2020-04-23 02:16:16 +03:00
|
|
|
// ascii 8 bit
|
2021-05-08 13:32:29 +03:00
|
|
|
if (re.flag & regex.f_bin) != 0 || unsafe { in_txt[i] } & 0x80 == 0 {
|
|
|
|
return u32(unsafe { in_txt[i] }), 1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
// unicode char
|
2021-05-08 13:32:29 +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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
ch = (ch << 8) | unsafe { in_txt[i + tmp] }
|
2020-01-13 15:30:41 +03:00
|
|
|
tmp++
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
return ch, char_len
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
[inline]
|
|
|
|
fn is_alnum(in_char byte) bool {
|
|
|
|
mut tmp := in_char - `A`
|
2021-05-08 13:32:29 +03:00
|
|
|
if tmp <= 25 {
|
|
|
|
return true
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
tmp = in_char - `a`
|
2021-05-08 13:32:29 +03:00
|
|
|
if tmp <= 25 {
|
|
|
|
return true
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
tmp = in_char - `0`
|
2021-05-08 13:32:29 +03:00
|
|
|
if tmp <= 9 {
|
|
|
|
return true
|
|
|
|
}
|
2021-08-14 08:47:12 +03:00
|
|
|
if in_char == `_` {
|
2021-05-08 13:32:29 +03:00
|
|
|
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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
return in_char in regex.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)
|
|
|
|
}
|
|
|
|
|
2021-08-14 08:47:12 +03:00
|
|
|
/*
|
2020-01-13 15:30:41 +03:00
|
|
|
[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)
|
|
|
|
}
|
2021-08-14 08:47:12 +03:00
|
|
|
*/
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
[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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
regex.compile_ok { return 'compile_ok' }
|
|
|
|
regex.no_match_found { return 'no_match_found' }
|
|
|
|
regex.err_char_unknown { return 'err_char_unknown' }
|
|
|
|
regex.err_undefined { return 'err_undefined' }
|
|
|
|
regex.err_internal_error { return 'err_internal_error' }
|
|
|
|
regex.err_cc_alloc_overflow { return 'err_cc_alloc_overflow' }
|
|
|
|
regex.err_syntax_error { return 'err_syntax_error' }
|
|
|
|
regex.err_groups_overflow { return 'err_groups_overflow' }
|
|
|
|
regex.err_groups_max_nested { return 'err_groups_max_nested' }
|
|
|
|
regex.err_group_not_balanced { return 'err_group_not_balanced' }
|
|
|
|
regex.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
|
2021-05-08 13:32:29 +03:00
|
|
|
mut res := ''
|
2020-01-14 04:45:08 +03:00
|
|
|
for i > 0 {
|
2020-12-03 21:33:53 +03:00
|
|
|
v := byte((ch >> ((i - 1) * 8)) & 0xFF)
|
2021-05-08 13:32:29 +03:00
|
|
|
if v != 0 {
|
|
|
|
res += '${v:1c}'
|
2020-01-14 04:45:08 +03:00
|
|
|
}
|
|
|
|
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
|
2021-05-08 13:32:29 +03:00
|
|
|
|
|
|
|
struct Token {
|
2020-01-13 15:30:41 +03:00
|
|
|
mut:
|
2020-08-27 07:46:18 +03:00
|
|
|
ist rune
|
2020-01-16 02:39:33 +03:00
|
|
|
// char
|
2021-05-08 13:32:29 +03:00
|
|
|
ch rune // char of the token if any
|
|
|
|
ch_len byte // char len
|
2020-01-13 15:30:41 +03:00
|
|
|
// Quantifiers / branch
|
2021-05-08 13:32:29 +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
|
|
|
|
greedy bool // greedy quantifier flag
|
2020-01-13 15:30:41 +03:00
|
|
|
// Char class
|
2021-05-08 13:32:29 +03:00
|
|
|
cc_index int = -1
|
2020-01-13 15:30:41 +03:00
|
|
|
// counters for quantifier check (repetitions)
|
2021-05-08 13:32:29 +03:00
|
|
|
rep int
|
2020-01-18 09:38:00 +03:00
|
|
|
// validator function pointer
|
2021-05-08 13:32:29 +03:00
|
|
|
validator FnValidator
|
2020-01-13 15:30:41 +03:00
|
|
|
// groups variables
|
2021-05-08 13:32:29 +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
|
2020-04-23 02:16:16 +03:00
|
|
|
// OR flag for the token
|
2021-05-08 13:32:29 +03:00
|
|
|
next_is_or bool // true if the next token is an OR
|
2020-12-18 07:57:31 +03:00
|
|
|
// dot_char token variables
|
2021-05-08 13:32:29 +03:00
|
|
|
dot_check_pc int = -1 // pc of the next token to check
|
|
|
|
last_dot_flag bool // if true indicate that is the last dot_char in the regex
|
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
|
|
|
|
}
|
|
|
|
|
2020-12-20 06:52:02 +03:00
|
|
|
/******************************************************************************
|
|
|
|
*
|
|
|
|
* Regex struct
|
|
|
|
*
|
|
|
|
******************************************************************************/
|
2020-01-13 15:30:41 +03:00
|
|
|
pub const (
|
2021-05-08 13:32:29 +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
|
2020-01-28 22:34:11 +03:00
|
|
|
|
2021-05-08 13:32:29 +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
|
2021-05-08 13:32:29 +03:00
|
|
|
f_src = 0x00020000 // search mode enabled
|
2020-01-13 15:30:41 +03:00
|
|
|
)
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
struct StateDotObj {
|
2020-01-13 15:30:41 +03:00
|
|
|
mut:
|
2021-05-08 13:32:29 +03:00
|
|
|
i int = -1 // char index in the input buffer
|
|
|
|
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
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
pub struct RE {
|
2020-01-13 15:30:41 +03:00
|
|
|
pub mut:
|
2021-05-08 13:32:29 +03:00
|
|
|
prog []Token
|
|
|
|
prog_len int // regex program len
|
2020-01-13 15:30:41 +03:00
|
|
|
// char classes storage
|
2021-05-08 13:32:29 +03:00
|
|
|
cc []CharClass // char class list
|
|
|
|
cc_index int // index
|
2020-01-13 15:30:41 +03:00
|
|
|
// groups
|
2021-05-08 13:32:29 +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
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
state_list []StateObj
|
2020-12-22 23:34:46 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
group_csave_flag bool // flag to enable continuous saving
|
|
|
|
group_csave []int //= []int{} // groups continuous save list
|
2020-01-25 21:12:23 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
group_map map[string]int // groups names map
|
2020-12-22 23:34:46 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
group_stack []int
|
|
|
|
group_data []int
|
2020-01-13 15:30:41 +03:00
|
|
|
// flags
|
2021-05-08 13:32:29 +03:00
|
|
|
flag int // flag for optional parameters
|
2020-01-13 15:30:41 +03:00
|
|
|
// Debug/log
|
2021-05-08 13:32:29 +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
|
2021-05-08 13:32:29 +03:00
|
|
|
[direct_array_access; inline]
|
|
|
|
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
|
2020-12-22 19:42:32 +03:00
|
|
|
for i < re.prog_len {
|
2020-12-03 21:33:53 +03:00
|
|
|
re.prog[i].group_rep = 0 // clear repetition of the group
|
2021-05-08 13:32:29 +03:00
|
|
|
re.prog[i].rep = 0 // clear repetition of the token
|
2020-01-13 15:30:41 +03:00
|
|
|
i++
|
|
|
|
}
|
2020-12-19 02:32:57 +03:00
|
|
|
|
|
|
|
// init groups array
|
|
|
|
if re.group_count > 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
re.groups = []int{len: re.group_count * 2, init: -1}
|
2020-12-19 02:32:57 +03:00
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-01-25 21:12:23 +03:00
|
|
|
// reset group_csave
|
2020-12-22 19:42:32 +03:00
|
|
|
if re.group_csave_flag == true {
|
|
|
|
re.group_csave.clear() // = []int{}
|
|
|
|
}
|
2021-07-14 22:20:05 +03:00
|
|
|
|
|
|
|
// reset state list
|
|
|
|
re.state_list.clear()
|
|
|
|
re.group_stack.clear()
|
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
|
2020-12-22 19:42:32 +03:00
|
|
|
//[inline]
|
|
|
|
[direct_array_access]
|
2021-05-08 13:32:29 +03:00
|
|
|
fn (mut re RE) reset_src() {
|
2020-01-31 04:29:54 +03:00
|
|
|
mut i := 0
|
2020-12-22 19:42:32 +03:00
|
|
|
for i < re.prog_len {
|
2020-12-03 21:33:53 +03:00
|
|
|
re.prog[i].group_rep = 0 // clear repetition of the group
|
2021-05-08 13:32:29 +03:00
|
|
|
re.prog[i].rep = 0 // clear repetition of the token
|
2020-01-31 04:29:54 +03:00
|
|
|
i++
|
|
|
|
}
|
2020-01-28 22:34:11 +03:00
|
|
|
}
|
|
|
|
|
2020-12-20 06:52:02 +03:00
|
|
|
/******************************************************************************
|
|
|
|
*
|
|
|
|
* Backslashes chars
|
|
|
|
*
|
|
|
|
******************************************************************************/
|
2020-01-13 15:30:41 +03:00
|
|
|
struct BslsStruct {
|
2021-05-08 13:32:29 +03:00
|
|
|
ch rune // meta char
|
|
|
|
validator FnValidator // validator function pointer
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +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 \
|
2021-05-08 13:32:29 +03:00
|
|
|
bsls_escape_list = [`\\`, `|`, `.`, `:`, `*`, `+`, `-`, `{`, `}`, `[`, `]`, `(`, `)`, `?`,
|
|
|
|
`^`, `!`]
|
2020-01-13 15:30:41 +03:00
|
|
|
)
|
|
|
|
|
|
|
|
enum BSLS_parse_state {
|
2021-05-08 13:32:29 +03:00
|
|
|
start
|
|
|
|
bsls_found
|
|
|
|
bsls_char
|
|
|
|
normal_char
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
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
|
2021-05-08 13:32:29 +03:00
|
|
|
fn (re RE) parse_bsls(in_txt string, in_i int) (int, int) {
|
2020-01-13 15:30:41 +03:00
|
|
|
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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
for c, x in regex.bsls_validator_array {
|
2020-01-13 15:30:41 +03:00
|
|
|
if x.ch == ch {
|
2021-05-08 13:32:29 +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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
if ch in regex.bsls_escape_list {
|
|
|
|
return regex.no_match_found, i - in_i + 1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
return regex.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
|
2021-05-08 13:32:29 +03:00
|
|
|
return regex.err_syntax_error, i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-12-20 06:52:02 +03:00
|
|
|
/******************************************************************************
|
|
|
|
*
|
|
|
|
* Char class
|
|
|
|
*
|
|
|
|
******************************************************************************/
|
2021-05-08 13:32:29 +03:00
|
|
|
const (
|
|
|
|
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:
|
2021-05-08 13:32:29 +03:00
|
|
|
cc_type int = regex.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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
buf := []byte{len: (re.cc.len)}
|
|
|
|
mut buf_ptr := unsafe { &byte(&buf) }
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
mut cc_i := re.prog[pc].cc_index
|
|
|
|
mut i := 0
|
|
|
|
mut tmp := 0
|
2021-05-08 13:32:29 +03:00
|
|
|
for cc_i >= 0 && cc_i < re.cc.len && re.cc[cc_i].cc_type != regex.cc_end {
|
|
|
|
if re.cc[cc_i].cc_type == regex.cc_bsls {
|
2020-07-22 20:28:53 +03:00
|
|
|
unsafe {
|
2021-04-27 01:41:42 +03:00
|
|
|
buf_ptr[i] = `\\`
|
|
|
|
i++
|
|
|
|
buf_ptr[i] = byte(re.cc[cc_i].ch0)
|
|
|
|
i++
|
2020-07-22 20:28:53 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
} else if re.cc[cc_i].ch0 == re.cc[cc_i].ch1 {
|
2020-01-13 15:30:41 +03:00
|
|
|
tmp = 3
|
|
|
|
for tmp >= 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
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 {
|
2021-04-27 01:41:42 +03:00
|
|
|
buf_ptr[i] = x
|
|
|
|
i++
|
2020-07-22 20:28:53 +03:00
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
tmp--
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
} else {
|
2020-01-13 15:30:41 +03:00
|
|
|
tmp = 3
|
|
|
|
for tmp >= 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
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 {
|
2021-04-27 01:41:42 +03:00
|
|
|
buf_ptr[i] = x
|
|
|
|
i++
|
2020-07-22 20:28:53 +03:00
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
tmp--
|
|
|
|
}
|
2020-07-22 20:28:53 +03:00
|
|
|
unsafe {
|
2021-04-27 01:41:42 +03:00
|
|
|
buf_ptr[i] = `-`
|
|
|
|
i++
|
2020-07-22 20:28:53 +03:00
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
tmp = 3
|
|
|
|
for tmp >= 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
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 {
|
2021-04-27 01:41:42 +03:00
|
|
|
buf_ptr[i] = x
|
|
|
|
i++
|
2020-07-22 20:28:53 +03:00
|
|
|
}
|
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)
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
return unsafe { tos_clone(buf_ptr) }
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
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
|
2021-05-08 13:32:29 +03:00
|
|
|
for cc_i >= 0 && cc_i < re.cc.len && re.cc[cc_i].cc_type != regex.cc_end {
|
|
|
|
if re.cc[cc_i].cc_type == regex.cc_bsls {
|
2020-01-13 15:30:41 +03:00
|
|
|
if re.cc[cc_i].validator(byte(ch)) {
|
|
|
|
return true
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
} else if ch >= re.cc[cc_i].ch0 && ch <= re.cc[cc_i].ch1 {
|
2020-01-13 15:30:41 +03:00
|
|
|
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
|
2021-05-08 13:32:29 +03:00
|
|
|
res_index := re.cc_index
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
mut cc_type := u32(regex.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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
return regex.err_cc_alloc_overflow, 0, u32(0)
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// get our char
|
2021-05-08 13:32:29 +03:00
|
|
|
char_tmp, char_len := re.get_char(in_txt, i)
|
2020-01-13 15:30:41 +03:00
|
|
|
ch := byte(char_tmp)
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("CC #${i:3d} ch: ${ch:c}")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// negation
|
|
|
|
if status == .start && ch == `^` {
|
2021-05-08 13:32:29 +03:00
|
|
|
cc_type = u32(regex.ist_char_class_neg)
|
2020-01-13 15:30:41 +03:00
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-05-16 18:11:13 +03:00
|
|
|
// minus symbol
|
|
|
|
if status == .start && ch == `-` {
|
2021-05-08 13:32:29 +03:00
|
|
|
re.cc[tmp_index].cc_type = regex.cc_char
|
|
|
|
re.cc[tmp_index].ch0 = char_tmp
|
|
|
|
re.cc[tmp_index].ch1 = char_tmp
|
2020-05-16 18:11:13 +03:00
|
|
|
i += char_len
|
|
|
|
tmp_index++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// bsls
|
|
|
|
if (status == .start || status == .in_char) && ch == `\\` {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("CC bsls.")
|
2020-01-13 15:30:41 +03:00
|
|
|
status = .in_bsls
|
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
if status == .in_bsls {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("CC bsls validation.")
|
|
|
|
for c, x in regex.bsls_validator_array {
|
2020-01-13 15:30:41 +03:00
|
|
|
if x.ch == ch {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("CC bsls found [${ch:c}]")
|
|
|
|
re.cc[tmp_index].cc_type = regex.cc_bsls
|
|
|
|
re.cc[tmp_index].ch0 = regex.bsls_validator_array[c].ch
|
|
|
|
re.cc[tmp_index].ch1 = regex.bsls_validator_array[c].ch
|
|
|
|
re.cc[tmp_index].validator = regex.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 {
|
2021-03-27 19:15:06 +03:00
|
|
|
// manage as a simple char
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("CC bsls not found [${ch:c}]")
|
|
|
|
re.cc[tmp_index].cc_type = regex.cc_char
|
|
|
|
re.cc[tmp_index].ch0 = char_tmp
|
|
|
|
re.cc[tmp_index].ch1 = char_tmp
|
2021-03-27 19:15:06 +03:00
|
|
|
i += char_len
|
|
|
|
tmp_index++
|
2020-01-13 15:30:41 +03:00
|
|
|
status = .in_char
|
2021-03-27 19:15:06 +03:00
|
|
|
continue
|
2021-05-08 13:32:29 +03:00
|
|
|
} else {
|
2020-01-13 15:30:41 +03:00
|
|
|
continue
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// simple char
|
2021-05-08 13:32:29 +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
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
re.cc[tmp_index].cc_type = regex.cc_char
|
|
|
|
re.cc[tmp_index].ch0 = char_tmp
|
|
|
|
re.cc[tmp_index].ch1 = char_tmp
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
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
|
2021-05-08 13:32:29 +03:00
|
|
|
re.cc[tmp_index - 1].cc_type = regex.cc_int
|
|
|
|
re.cc[tmp_index - 1].ch1 = char_tmp
|
2020-01-13 15:30:41 +03:00
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// char class end
|
|
|
|
if status == .in_char && ch == `]` {
|
2021-05-08 13:32:29 +03:00
|
|
|
re.cc[tmp_index].cc_type = regex.cc_end
|
|
|
|
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
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
return res_index, i - in_i + 2, cc_type
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
i++
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
return regex.err_syntax_error, 0, u32(0)
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-12-20 06:52:02 +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]
|
|
|
|
}
|
2021-05-08 13:32:29 +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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
return regex.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
|
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if status == .start && is_digit(ch) {
|
2020-01-13 15:30:41 +03:00
|
|
|
status = .min_parse
|
|
|
|
q_min *= 10
|
|
|
|
q_min += int(ch - `0`)
|
|
|
|
i++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if status == .min_parse && is_digit(ch) {
|
2020-01-13 15:30:41 +03:00
|
|
|
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 == `}` {
|
2021-05-08 13:32:29 +03:00
|
|
|
q_max = regex.max_quantifier
|
2020-01-16 02:39:33 +03:00
|
|
|
status = .greedy
|
|
|
|
continue
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// start max parsing
|
2021-05-08 13:32:29 +03:00
|
|
|
if status == .comma_checked && is_digit(ch) {
|
2020-01-13 15:30:41 +03:00
|
|
|
status = .max_parse
|
|
|
|
q_max *= 10
|
|
|
|
q_max += int(ch - `0`)
|
|
|
|
i++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// parse the max
|
2021-05-08 13:32:29 +03:00
|
|
|
if status == .max_parse && is_digit(ch) {
|
2020-01-13 15:30:41 +03:00
|
|
|
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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
if i + 1 < in_txt.len {
|
2020-01-16 02:39:33 +03:00
|
|
|
i++
|
|
|
|
status = .gredy_parse
|
|
|
|
continue
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
return q_min, q_max, i - in_i + 2, false
|
2020-01-16 02:39:33 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// check the greedy flag
|
|
|
|
if status == .gredy_parse {
|
|
|
|
if ch == `?` {
|
2021-05-08 13:32:29 +03:00
|
|
|
return q_min, q_max, i - in_i + 2, true
|
2020-01-16 02:39:33 +03:00
|
|
|
} else {
|
|
|
|
i--
|
2021-05-08 13:32:29 +03:00
|
|
|
return q_min, q_max, i - in_i + 2, false
|
2020-01-16 02:39:33 +03:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// not a {} quantifier, exit
|
2021-05-08 13:32:29 +03:00
|
|
|
return regex.err_syntax_error, i, 0, false
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// not a conform {} quantifier
|
2021-05-08 13:32:29 +03:00
|
|
|
return regex.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
|
2021-05-08 13:32:29 +03:00
|
|
|
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
|
2021-05-08 13:32:29 +03:00
|
|
|
char_tmp, char_len := re.get_char(in_txt, i)
|
2020-01-28 22:34:11 +03:00
|
|
|
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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("NO VALID Q MARK")
|
|
|
|
return -2, true, name, i
|
2020-01-28 22:34:11 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
if status == .p_status && ch == `<` {
|
|
|
|
status = .p_start
|
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
if status == .p_start && ch != `>` {
|
|
|
|
status = .p_in_name
|
2021-05-08 13:32:29 +03:00
|
|
|
name += '${ch:1c}' // TODO: manage utf8 chars
|
2020-01-28 22:34:11 +03:00
|
|
|
i += char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// colect name
|
|
|
|
if status == .p_in_name && ch != `>` && is_alnum(ch) {
|
2021-05-08 13:32:29 +03:00
|
|
|
name += '${ch:1c}' // TODO: manage utf8 chars
|
2020-01-28 22:34:11 +03:00
|
|
|
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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
return -2, true, name, i
|
2020-01-28 22:34:11 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// normal group, nothig to do, exit
|
2021-05-08 13:32:29 +03:00
|
|
|
return 0, true, name, i
|
2020-01-28 22:34:11 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
// UNREACHABLE
|
|
|
|
// println("ERROR!! NOT MEANT TO BE HERE!!1")
|
|
|
|
return -2, true, name, i
|
2020-01-28 22:34:11 +03:00
|
|
|
}
|
|
|
|
|
2021-09-05 04:48:59 +03:00
|
|
|
const (
|
|
|
|
quntifier_chars = [rune(`+`), `*`, `?`, `{`]
|
|
|
|
)
|
|
|
|
|
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
|
2021-05-08 13:32:29 +03:00
|
|
|
fn (mut re RE) impl_compile(in_txt string) (int, int) {
|
|
|
|
mut i := 0 // input string index
|
|
|
|
mut pc := 0 // program counter
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// group management variables
|
2021-05-08 13:32:29 +03:00
|
|
|
mut group_count := -1
|
|
|
|
mut group_stack := []int{len: re.group_max_nested, init: 0}
|
2020-12-19 02:32:57 +03:00
|
|
|
mut group_stack_txt_index := []int{len: re.group_max_nested, init: -1}
|
2021-05-08 13:32:29 +03:00
|
|
|
mut group_stack_index := -1
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
re.query = in_txt // save the query string
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
i = 0
|
|
|
|
for i < in_txt.len {
|
|
|
|
mut char_tmp := u32(0)
|
|
|
|
mut char_len := 0
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("i: ${i:3d} ch: ${in_txt.str[i]:c}")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2021-05-08 13:32:29 +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) == `^` {
|
2021-05-08 13:32:29 +03:00
|
|
|
re.flag = regex.f_ms
|
2020-01-13 15:30:41 +03:00
|
|
|
i = i + char_len
|
|
|
|
continue
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
if char_len == 1 && i == (in_txt.len - 1) && byte(char_tmp) == `$` {
|
|
|
|
re.flag = regex.f_me
|
2020-01-13 15:30:41 +03:00
|
|
|
i = i + char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
// ist_group_start
|
2020-01-13 15:30:41 +03:00
|
|
|
if char_len == 1 && pc >= 0 && byte(char_tmp) == `(` {
|
2021-05-08 13:32:29 +03:00
|
|
|
// check max groups allowed
|
2020-01-13 15:30:41 +03:00
|
|
|
if group_count > re.group_max {
|
2021-05-08 13:32:29 +03:00
|
|
|
return regex.err_groups_overflow, i + 1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
group_stack_index++
|
|
|
|
|
|
|
|
// check max nested groups allowed
|
|
|
|
if group_stack_index > re.group_max_nested {
|
2021-05-08 13:32:29 +03:00
|
|
|
return regex.err_groups_max_nested, i + 1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
tmp_res, cgroup_flag, cgroup_name, next_i := re.parse_groups(in_txt, i)
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-28 22:34:11 +03:00
|
|
|
// manage question mark format error
|
|
|
|
if tmp_res < -1 {
|
2021-05-08 13:32:29 +03:00
|
|
|
return regex.err_group_qm_notation, next_i
|
2020-01-28 22:34:11 +03:00
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Parse group: [$tmp_res, $cgroup_flag, ($i,$next_i), '${in_txt[i..next_i]}' ]")
|
2020-01-28 22:34:11 +03:00
|
|
|
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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
// 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
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
re.prog[pc].ist = u32(0) | regex.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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
// 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
|
2021-05-08 13:32:29 +03:00
|
|
|
if char_len == 1 && pc > 0 && byte(char_tmp) == `)` {
|
2020-01-13 15:30:41 +03:00
|
|
|
if group_stack_index < 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
return regex.err_group_not_balanced, i + 1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
goto_pc := group_stack[group_stack_index]
|
|
|
|
group_stack_index--
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
re.prog[pc].ist = u32(0) | regex.ist_group_end
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[pc].rep_min = 1
|
|
|
|
re.prog[pc].rep_max = 1
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
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
|
|
|
|
2021-05-08 13:32:29 +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
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
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
|
2021-05-08 13:32:29 +03:00
|
|
|
if char_len == 1 && pc >= 0 && byte(char_tmp) == `.` {
|
|
|
|
re.prog[pc].ist = u32(0) | regex.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
|
2021-05-08 13:32:29 +03:00
|
|
|
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
|
2021-05-08 13:32:29 +03:00
|
|
|
if pc > 0 && re.prog[pc - 1].ist == regex.ist_or_branch {
|
|
|
|
return regex.err_syntax_error, i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
re.prog[pc].ist = u32(0) | regex.ist_or_branch
|
2020-01-13 15:30:41 +03:00
|
|
|
pc = pc + 1
|
|
|
|
i = i + char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// Quantifiers
|
2021-05-08 13:32:29 +03:00
|
|
|
if char_len == 1 && pc > 0 {
|
2021-09-05 04:48:59 +03:00
|
|
|
mut char_next := rune(0)
|
|
|
|
mut char_next_len := 0
|
|
|
|
if (char_len + i) < in_txt.len {
|
|
|
|
char_next, char_next_len = re.get_char(in_txt, i + char_len)
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
mut quant_flag := true
|
|
|
|
match byte(char_tmp) {
|
|
|
|
`?` {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("q: ${char_tmp:c}")
|
2021-09-05 04:48:59 +03:00
|
|
|
// check illegal quantifier sequences
|
|
|
|
if char_next_len == 1 && char_next in regex.quntifier_chars {
|
|
|
|
return regex.err_syntax_error, i
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
re.prog[pc - 1].rep_min = 0
|
|
|
|
re.prog[pc - 1].rep_max = 1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
`+` {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("q: ${char_tmp:c}")
|
2021-09-05 04:48:59 +03:00
|
|
|
// check illegal quantifier sequences
|
|
|
|
if char_next_len == 1 && char_next in regex.quntifier_chars {
|
|
|
|
return regex.err_syntax_error, i
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
re.prog[pc - 1].rep_min = 1
|
|
|
|
re.prog[pc - 1].rep_max = regex.max_quantifier
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
`*` {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("q: ${char_tmp:c}")
|
2021-09-05 04:48:59 +03:00
|
|
|
// check illegal quantifier sequences
|
|
|
|
if char_next_len == 1 && char_next in regex.quntifier_chars {
|
|
|
|
return regex.err_syntax_error, i
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
re.prog[pc - 1].rep_min = 0
|
|
|
|
re.prog[pc - 1].rep_max = regex.max_quantifier
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
`{` {
|
2021-05-08 13:32:29 +03:00
|
|
|
min, max, tmp, greedy := re.parse_quantifier(in_txt, i + 1)
|
2020-01-13 15:30:41 +03:00
|
|
|
// it is a quantifier
|
|
|
|
if min >= 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("{$min,$max}\n str:[${in_txt[i..i+tmp]}] greedy:$greedy")
|
2020-01-13 15:30:41 +03:00
|
|
|
i = i + tmp
|
2021-05-08 13:32:29 +03:00
|
|
|
re.prog[pc - 1].rep_min = min
|
|
|
|
re.prog[pc - 1].rep_max = max
|
|
|
|
re.prog[pc - 1].greedy = greedy
|
2021-09-05 04:48:59 +03:00
|
|
|
// check illegal quantifier sequences
|
|
|
|
if i <= in_txt.len {
|
|
|
|
char_next, char_next_len = re.get_char(in_txt, i)
|
|
|
|
if char_next_len == 1 && char_next in regex.quntifier_chars {
|
|
|
|
return regex.err_syntax_error, i
|
|
|
|
}
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
continue
|
2021-05-08 13:32:29 +03:00
|
|
|
} else {
|
|
|
|
return min, i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2021-09-05 04:48:59 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// TODO: decide if the open bracket can be conform without the close bracket
|
|
|
|
/*
|
|
|
|
// no conform, parse as normal char
|
|
|
|
else {
|
|
|
|
quant_flag = false
|
|
|
|
}
|
|
|
|
*/
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
else {
|
2020-01-13 15:30:41 +03:00
|
|
|
quant_flag = false
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if quant_flag {
|
|
|
|
i = i + char_len
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-01-16 02:39:33 +03:00
|
|
|
// IST_CHAR_CLASS_*
|
2021-05-08 13:32:29 +03:00
|
|
|
if char_len == 1 && pc >= 0 {
|
2020-01-13 15:30:41 +03:00
|
|
|
if byte(char_tmp) == `[` {
|
2021-05-08 13:32:29 +03:00
|
|
|
cc_index, tmp, cc_type := re.parse_char_class(in_txt, i + 1)
|
2020-01-13 15:30:41 +03:00
|
|
|
if cc_index >= 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("index: $cc_index str:${in_txt[i..i+tmp]}")
|
2020-01-13 15:30:41 +03:00
|
|
|
i = i + tmp
|
2021-05-08 13:32:29 +03:00
|
|
|
re.prog[pc].ist = u32(0) | cc_type
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[pc].cc_index = cc_index
|
2021-05-08 13:32:29 +03:00
|
|
|
re.prog[pc].rep_min = 1
|
|
|
|
re.prog[pc].rep_max = 1
|
2020-01-13 15:30:41 +03:00
|
|
|
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
|
2021-05-08 13:32:29 +03:00
|
|
|
if char_len == 1 && pc >= 0 {
|
2020-01-13 15:30:41 +03:00
|
|
|
if byte(char_tmp) == `\\` {
|
2021-05-08 13:32:29 +03:00
|
|
|
bsls_index, tmp := re.parse_bsls(in_txt, i)
|
|
|
|
// 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
|
2021-05-08 13:32:29 +03:00
|
|
|
re.prog[pc].ist = u32(0) | regex.ist_bsls_char
|
|
|
|
re.prog[pc].rep_min = 1
|
|
|
|
re.prog[pc].rep_max = 1
|
|
|
|
re.prog[pc].validator = regex.bsls_validator_array[bsls_index].validator
|
|
|
|
re.prog[pc].ch = regex.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
|
2021-05-08 13:32:29 +03:00
|
|
|
else if bsls_index == regex.no_match_found {
|
2020-01-13 15:30:41 +03:00
|
|
|
i += char_len
|
2021-05-08 13:32:29 +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 {
|
2021-05-08 13:32:29 +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
|
2021-05-08 13:32:29 +03:00
|
|
|
re.prog[pc].ist = regex.ist_simple_char
|
|
|
|
re.prog[pc].ch = char_tmp
|
|
|
|
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
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("char: ${char_tmp:c}")
|
|
|
|
pc = pc + 1
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
i += char_len
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// add end of the program
|
2021-05-08 13:32:29 +03:00
|
|
|
re.prog[pc].ist = regex.ist_prog_end
|
2020-12-22 19:42:32 +03:00
|
|
|
re.prog_len = pc
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// check for unbalanced groups
|
|
|
|
if group_stack_index != -1 {
|
2021-05-08 13:32:29 +03:00
|
|
|
return regex.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
|
2021-05-08 13:32:29 +03:00
|
|
|
if pc > 0 && re.prog[pc - 1].ist == regex.ist_or_branch {
|
|
|
|
return regex.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
|
|
|
|
//******************************************
|
|
|
|
|
2020-12-13 04:04:53 +03:00
|
|
|
//
|
|
|
|
// manage ist_dot_char
|
|
|
|
//
|
2020-12-18 07:57:31 +03:00
|
|
|
|
|
|
|
// find the checks for dot chars, if any...
|
2020-01-13 15:30:41 +03:00
|
|
|
mut pc1 := 0
|
2020-12-18 07:57:31 +03:00
|
|
|
mut dot_char_count := 0
|
|
|
|
mut last_dot_char_pc := -1
|
2020-01-13 15:30:41 +03:00
|
|
|
for pc1 < pc {
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[pc1].ist == regex.ist_dot_char {
|
|
|
|
// println("Dot_char pc: $pc1")
|
2020-12-18 07:57:31 +03:00
|
|
|
last_dot_char_pc = pc1
|
|
|
|
dot_char_count++
|
|
|
|
mut pc2 := pc1 + 1
|
|
|
|
for pc2 < pc {
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[pc2].ist == regex.ist_dot_char {
|
|
|
|
return regex.err_syntax_error, 0
|
2020-12-18 07:57:31 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[pc2].ist !in [rune(regex.ist_prog_end), regex.ist_group_end,
|
2021-09-21 16:20:09 +03:00
|
|
|
regex.ist_group_start] {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Next dot char check is PC: ${pc2}")
|
2020-12-18 07:57:31 +03:00
|
|
|
re.prog[pc1].dot_check_pc = pc2
|
|
|
|
break
|
|
|
|
}
|
|
|
|
pc2++
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
pc1++
|
|
|
|
}
|
2020-01-18 09:38:00 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("last_dot_char_pc: $last_dot_char_pc")
|
2020-12-18 07:57:31 +03:00
|
|
|
if last_dot_char_pc >= 0 {
|
|
|
|
pc1 = last_dot_char_pc + 1
|
|
|
|
mut is_last_dot := true
|
|
|
|
for pc1 < pc {
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[pc1].ist !in [rune(regex.ist_prog_end), regex.ist_group_end] {
|
2020-12-18 07:57:31 +03:00
|
|
|
is_last_dot = false
|
2020-12-13 04:04:53 +03:00
|
|
|
break
|
|
|
|
}
|
2020-12-18 07:57:31 +03:00
|
|
|
pc1++
|
|
|
|
}
|
|
|
|
if is_last_dot {
|
|
|
|
re.prog[last_dot_char_pc].last_dot_flag = true
|
2020-12-13 04:04:53 +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
|
2021-05-08 13:32:29 +03:00
|
|
|
for pc1 < pc - 2 {
|
|
|
|
// println("Here $pc1 ${pc-2}")
|
2020-01-13 15:30:41 +03:00
|
|
|
// two consecutive OR are a syntax error
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[pc1 + 1].ist == regex.ist_or_branch
|
|
|
|
&& re.prog[pc1 + 2].ist == regex.ist_or_branch {
|
|
|
|
return regex.err_syntax_error, i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// manange a|b chains like a|(b)|c|d...
|
|
|
|
// standard solution
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[pc1].ist != regex.ist_or_branch && re.prog[pc1 + 1].ist == regex.ist_or_branch
|
|
|
|
&& re.prog[pc1 + 2].ist != regex.ist_or_branch {
|
|
|
|
re.prog[pc1].next_is_or = true // set that the next token is an OR
|
|
|
|
re.prog[pc1 + 1].rep_min = pc1 + 2 // failed match jump
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// match jump, if an OR chain the next token will be an OR token
|
2021-05-08 13:32:29 +03:00
|
|
|
mut pc2 := pc1 + 2
|
|
|
|
for pc2 < pc - 1 {
|
2020-01-13 15:30:41 +03:00
|
|
|
ist := re.prog[pc2].ist
|
2021-05-08 13:32:29 +03:00
|
|
|
if ist == regex.ist_group_start {
|
|
|
|
re.prog[pc1 + 1].rep_max = re.prog[pc2].goto_pc + 1
|
2020-01-13 15:30:41 +03:00
|
|
|
break
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
if ist != regex.ist_or_branch {
|
|
|
|
re.prog[pc1 + 1].rep_max = pc2 + 1
|
2020-01-13 15:30:41 +03:00
|
|
|
break
|
|
|
|
}
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
pc2++
|
|
|
|
}
|
2020-12-05 03:51:48 +03:00
|
|
|
// special case query of few chars, teh true can't go on the first instruction
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[pc1 + 1].rep_max == pc1 {
|
|
|
|
re.prog[pc1 + 1].rep_max = 3
|
2020-12-05 03:51:48 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Compile OR postproc. [$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()
|
2021-05-08 13:32:29 +03:00
|
|
|
re.log_func(gc)
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
//******************************************
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
return regex.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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
mut pc1 := 0
|
|
|
|
mut res := strings.new_builder(re.cc.len * 2 * re.prog.len)
|
|
|
|
res.write_string('========================================\nv RegEx compiler v $regex.v_regex_version output:\n')
|
|
|
|
|
|
|
|
mut stop_flag := false
|
|
|
|
|
|
|
|
for pc1 <= re.prog.len {
|
|
|
|
tk := re.prog[pc1]
|
|
|
|
res.write_string('PC:${pc1:3d}')
|
|
|
|
|
|
|
|
res.write_string(' ist: ')
|
|
|
|
res.write_string('${tk.ist:8x}'.replace(' ', '0'))
|
|
|
|
res.write_string(' ')
|
|
|
|
ist := tk.ist
|
|
|
|
if ist == regex.ist_bsls_char {
|
|
|
|
res.write_string('[\\${tk.ch:1c}] BSLS')
|
|
|
|
} else if ist == regex.ist_prog_end {
|
|
|
|
res.write_string('PROG_END')
|
|
|
|
stop_flag = true
|
|
|
|
} else if ist == regex.ist_or_branch {
|
|
|
|
res.write_string('OR ')
|
|
|
|
} else if ist == regex.ist_char_class_pos {
|
|
|
|
res.write_string('[${re.get_char_class(pc1)}] CHAR_CLASS_POS')
|
|
|
|
} else if ist == regex.ist_char_class_neg {
|
|
|
|
res.write_string('[^${re.get_char_class(pc1)}] CHAR_CLASS_NEG')
|
|
|
|
} else if ist == regex.ist_dot_char {
|
|
|
|
res.write_string('. DOT_CHAR nx chk: $tk.dot_check_pc')
|
|
|
|
if tk.last_dot_flag == true {
|
|
|
|
res.write_string(' last!')
|
|
|
|
}
|
|
|
|
} else if ist == regex.ist_group_start {
|
|
|
|
res.write_string('( GROUP_START #:$tk.group_id')
|
|
|
|
if tk.group_id == -1 {
|
|
|
|
res.write_string(' ?:')
|
|
|
|
} else {
|
|
|
|
for x in re.group_map.keys() {
|
|
|
|
if re.group_map[x] == (tk.group_id + 1) {
|
|
|
|
res.write_string(' ?P<$x>')
|
|
|
|
break
|
2020-01-28 22:34:11 +03:00
|
|
|
}
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
} else if ist == regex.ist_group_end {
|
|
|
|
res.write_string(') GROUP_END #:$tk.group_id')
|
|
|
|
} else if ist == regex.ist_simple_char {
|
|
|
|
res.write_string('[${tk.ch:1c}] query_ch')
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if tk.rep_max == regex.max_quantifier {
|
|
|
|
res.write_string(' {${tk.rep_min:3d},MAX}')
|
|
|
|
} else {
|
|
|
|
if ist == regex.ist_or_branch {
|
|
|
|
res.write_string(' if false go: ${tk.rep_min:3d} if true go: ${tk.rep_max:3d}')
|
|
|
|
} else {
|
|
|
|
res.write_string(' {${tk.rep_min:3d},${tk.rep_max:3d}}')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
if tk.greedy == true {
|
|
|
|
res.write_string('?')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
res.write_string('\n')
|
|
|
|
if stop_flag {
|
|
|
|
break
|
|
|
|
}
|
|
|
|
pc1++
|
|
|
|
}
|
|
|
|
|
|
|
|
res.write_string('========================================\n')
|
|
|
|
return res.str()
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// get_query return a string with a reconstruction of the query starting from the regex program code
|
|
|
|
pub fn (re RE) get_query() string {
|
2021-05-08 13:32:29 +03:00
|
|
|
mut res := strings.new_builder(re.query.len * 2)
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if (re.flag & regex.f_ms) != 0 {
|
|
|
|
res.write_string('^')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
mut i := 0
|
2021-05-08 13:32:29 +03:00
|
|
|
for i < re.prog.len && re.prog[i].ist != regex.ist_prog_end && re.prog[i].ist != 0 {
|
2020-10-05 14:08:30 +03:00
|
|
|
tk := unsafe { &re.prog[i] }
|
2020-01-25 21:12:23 +03:00
|
|
|
ch := tk.ist
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// GROUP start
|
2021-05-08 13:32:29 +03:00
|
|
|
if ch == regex.ist_group_start {
|
2020-01-13 15:30:41 +03:00
|
|
|
if re.debug == 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
res.write_string('(')
|
2020-01-13 15:30:41 +03:00
|
|
|
} else {
|
2020-01-28 22:34:11 +03:00
|
|
|
if tk.group_id == -1 {
|
2021-05-08 13:32:29 +03:00
|
|
|
res.write_string('(?:') // non capturing group
|
2020-01-28 22:34:11 +03:00
|
|
|
} else {
|
2021-05-08 13:32:29 +03:00
|
|
|
res.write_string('#${tk.group_id}(')
|
2020-01-28 22:34:11 +03:00
|
|
|
}
|
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() {
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.group_map[x] == (tk.group_id + 1) {
|
|
|
|
res.write_string('?P<$x>')
|
2020-01-28 22:34:11 +03:00
|
|
|
break
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
i++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// GROUP end
|
2021-05-08 13:32:29 +03:00
|
|
|
if ch == regex.ist_group_end {
|
|
|
|
res.write_string(')')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// OR branch
|
2021-05-08 13:32:29 +03:00
|
|
|
if ch == regex.ist_or_branch {
|
|
|
|
res.write_string('|')
|
2020-01-13 15:30:41 +03:00
|
|
|
if re.debug > 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
res.write_string('{$tk.rep_min,$tk.rep_max}')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
i++
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// char class
|
2021-05-08 13:32:29 +03:00
|
|
|
if ch == regex.ist_char_class_neg || ch == regex.ist_char_class_pos {
|
|
|
|
res.write_string('[')
|
|
|
|
if ch == regex.ist_char_class_neg {
|
|
|
|
res.write_string('^')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
res.write_string('${re.get_char_class(i)}')
|
|
|
|
res.write_string(']')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// bsls char
|
2021-05-08 13:32:29 +03:00
|
|
|
if ch == regex.ist_bsls_char {
|
|
|
|
res.write_string('\\${tk.ch:1c}')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
// ist_dot_char
|
2021-05-08 13:32:29 +03:00
|
|
|
if ch == regex.ist_dot_char {
|
|
|
|
res.write_string('.')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// char alone
|
2021-05-08 13:32:29 +03:00
|
|
|
if ch == regex.ist_simple_char {
|
|
|
|
if byte(ch) in regex.bsls_escape_list {
|
|
|
|
res.write_string('\\')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
res.write_string('${tk.ch:c}')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// quantifier
|
2020-01-25 21:12:23 +03:00
|
|
|
if !(tk.rep_min == 1 && tk.rep_max == 1) {
|
|
|
|
if tk.rep_min == 0 && tk.rep_max == 1 {
|
2021-05-08 13:32:29 +03:00
|
|
|
res.write_string('?')
|
|
|
|
} else if tk.rep_min == 1 && tk.rep_max == regex.max_quantifier {
|
|
|
|
res.write_string('+')
|
|
|
|
} else if tk.rep_min == 0 && tk.rep_max == regex.max_quantifier {
|
|
|
|
res.write_string('*')
|
2020-01-13 15:30:41 +03:00
|
|
|
} else {
|
2021-05-08 13:32:29 +03:00
|
|
|
if tk.rep_max == regex.max_quantifier {
|
|
|
|
res.write_string('{$tk.rep_min,MAX}')
|
2020-01-13 15:30:41 +03:00
|
|
|
} else {
|
2021-05-08 13:32:29 +03:00
|
|
|
res.write_string('{$tk.rep_min,$tk.rep_max}')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-01-25 21:12:23 +03:00
|
|
|
if tk.greedy == true {
|
2021-05-08 13:32:29 +03:00
|
|
|
res.write_string('?')
|
2020-01-16 02:39:33 +03:00
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
}
|
|
|
|
i++
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
if (re.flag & regex.f_me) != 0 {
|
|
|
|
res.write_string('$')
|
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
|
|
|
}
|
|
|
|
|
2020-12-20 06:52:02 +03:00
|
|
|
/******************************************************************************
|
|
|
|
*
|
|
|
|
* Groups saving utilities
|
|
|
|
*
|
|
|
|
******************************************************************************/
|
2020-12-22 19:42:32 +03:00
|
|
|
[direct_array_access]
|
2020-12-14 16:02:13 +03:00
|
|
|
fn (mut re RE) group_continuous_save(g_index int) {
|
|
|
|
if re.group_csave_flag == true {
|
|
|
|
// continuous save, save until we have space
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2020-12-14 16:02:13 +03:00
|
|
|
// init the first element as counter
|
|
|
|
if re.group_csave.len == 0 {
|
|
|
|
re.group_csave << 0
|
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
gi := g_index >> 1
|
2020-12-14 16:02:13 +03:00
|
|
|
start := re.groups[g_index]
|
2021-05-08 13:32:29 +03:00
|
|
|
end := re.groups[g_index + 1]
|
2020-12-14 16:02:13 +03:00
|
|
|
|
|
|
|
// check if we are simply increasing the size ot the found group
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.group_csave.len >= 4 && gi == re.group_csave[re.group_csave.len - 3]
|
|
|
|
&& start == re.group_csave[re.group_csave.len - 2] {
|
2020-12-14 16:02:13 +03:00
|
|
|
re.group_csave[re.group_csave.len - 1] = end
|
|
|
|
return
|
|
|
|
}
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2020-12-14 16:02:13 +03:00
|
|
|
// otherwise append a new group to the list
|
|
|
|
|
|
|
|
// increment counter
|
|
|
|
re.group_csave[0]++
|
|
|
|
// save the record
|
2021-05-08 13:32:29 +03:00
|
|
|
re.group_csave << (g_index >> 1) // group id
|
|
|
|
re.group_csave << re.groups[g_index] // start
|
|
|
|
re.group_csave << re.groups[g_index + 1] // end
|
2020-12-14 16:02:13 +03:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-12-20 06:52:02 +03:00
|
|
|
/******************************************************************************
|
|
|
|
*
|
|
|
|
* Matching
|
|
|
|
*
|
2021-01-18 15:20:06 +03:00
|
|
|
******************************************************************************/
|
2021-05-08 13:32:29 +03:00
|
|
|
enum Match_state {
|
2020-04-23 02:16:16 +03:00
|
|
|
start = 0
|
|
|
|
stop
|
|
|
|
end
|
|
|
|
new_line
|
2021-05-08 13:32:29 +03:00
|
|
|
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
|
2020-04-23 02:16:16 +03:00
|
|
|
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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
match s {
|
|
|
|
.start { return 'start' }
|
|
|
|
.stop { return 'stop' }
|
|
|
|
.end { return 'end' }
|
|
|
|
.new_line { return 'new line' }
|
|
|
|
.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:
|
2021-05-08 13:32:29 +03:00
|
|
|
group_index int = -1 // group id used to know how many groups are open
|
|
|
|
match_flag bool // indicate if we are in a match condition
|
|
|
|
match_index int = -1 // index of the last match
|
|
|
|
first_match int = -1 // index of the first match
|
|
|
|
pc int = -1 // program counter
|
|
|
|
i int = -1 // source string index
|
|
|
|
char_len int // last char legth
|
|
|
|
last_dot_pc int = -1 // last dot chat pc
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-12-22 19:42:32 +03:00
|
|
|
[direct_array_access]
|
2021-05-08 13:32:29 +03:00
|
|
|
pub fn (mut re RE) match_base(in_txt &byte, in_txt_len int) (int, int) {
|
2020-01-13 15:30:41 +03:00
|
|
|
// result status
|
2021-05-08 13:32:29 +03:00
|
|
|
mut result := regex.no_match_found // function return
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
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
|
|
|
|
mut src_end := false
|
2020-12-05 03:51:48 +03:00
|
|
|
mut last_fnd_pc := -1
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
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
|
|
|
|
2021-05-08 13:32:29 +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()
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.debug > 0 {
|
2020-01-13 15:30:41 +03:00
|
|
|
// print header
|
2020-01-14 04:45:08 +03:00
|
|
|
mut h_buf := strings.new_builder(32)
|
2021-05-08 13:32:29 +03:00
|
|
|
h_buf.write_string('flags: ')
|
|
|
|
h_buf.write_string('${re.flag:8x}'.replace(' ', '0'))
|
|
|
|
h_buf.write_string('\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 {
|
2020-12-18 07:57:31 +03:00
|
|
|
if state.pc >= 0 && state.pc < re.prog.len {
|
|
|
|
ist = re.prog[state.pc].ist
|
2021-05-08 13:32:29 +03:00
|
|
|
} else if state.pc >= re.prog.len {
|
|
|
|
// println("ERROR!! PC overflow!!")
|
|
|
|
return regex.err_internal_error, state.i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
//******************************************
|
|
|
|
// DEBUG LOG
|
|
|
|
//******************************************
|
2021-05-08 13:32:29 +03:00
|
|
|
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
|
2020-12-18 07:57:31 +03:00
|
|
|
if state.i >= in_txt_len {
|
2021-05-08 13:32:29 +03:00
|
|
|
buf2.write_string('# ${step_count:3d} END OF INPUT TEXT\n')
|
2020-04-25 23:42:48 +03:00
|
|
|
sss := buf2.str()
|
|
|
|
re.log_func(sss)
|
2021-05-08 13:32:29 +03:00
|
|
|
} else {
|
2020-01-16 02:39:33 +03:00
|
|
|
// print only the exe instruction
|
2021-05-08 13:32:29 +03:00
|
|
|
if (re.debug == 1 && m_state == .ist_load) || re.debug == 2 {
|
|
|
|
if ist == regex.ist_prog_end {
|
|
|
|
buf2.write_string('# ${step_count:3d} PROG_END\n')
|
|
|
|
} else if ist == 0 || m_state in [.start, .ist_next, .stop] {
|
|
|
|
buf2.write_string('# ${step_count:3d} s: ${state_str(m_state):12s} PC: NA\n')
|
|
|
|
} else {
|
2020-12-18 07:57:31 +03:00
|
|
|
ch, char_len = re.get_charb(in_txt, state.i)
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
buf2.write_string('# ${step_count:3d} s: ${state_str(m_state):12s} PC: ${state.pc:3d}=>')
|
|
|
|
buf2.write_string('${ist:8x}'.replace(' ', '0'))
|
|
|
|
buf2.write_string(" i,ch,len:[${state.i:3d},'${utf8_str(ch)}',$char_len] f.m:[${state.first_match:3d},${state.match_index:3d}] ")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if ist == regex.ist_simple_char {
|
|
|
|
buf2.write_string('query_ch: [${re.prog[state.pc].ch:1c}]')
|
2020-01-13 15:30:41 +03:00
|
|
|
} else {
|
2021-05-08 13:32:29 +03:00
|
|
|
if ist == regex.ist_bsls_char {
|
|
|
|
buf2.write_string('BSLS [\\${re.prog[state.pc].ch:1c}]')
|
|
|
|
} else if ist == regex.ist_prog_end {
|
|
|
|
buf2.write_string('PROG_END')
|
|
|
|
} else if ist == regex.ist_or_branch {
|
|
|
|
buf2.write_string('OR')
|
|
|
|
} else if ist == regex.ist_char_class_pos {
|
|
|
|
buf2.write_string('CHAR_CLASS_POS[${re.get_char_class(state.pc)}]')
|
|
|
|
} else if ist == regex.ist_char_class_neg {
|
|
|
|
buf2.write_string('CHAR_CLASS_NEG[${re.get_char_class(state.pc)}]')
|
|
|
|
} else if ist == regex.ist_dot_char {
|
|
|
|
buf2.write_string('DOT_CHAR')
|
|
|
|
} else if ist == regex.ist_group_start {
|
|
|
|
tmp_gi := re.prog[state.pc].group_id
|
2020-12-18 07:57:31 +03:00
|
|
|
tmp_gr := re.prog[re.prog[state.pc].goto_pc].group_rep
|
2021-05-08 13:32:29 +03:00
|
|
|
buf2.write_string('GROUP_START #:$tmp_gi rep:$tmp_gr ')
|
|
|
|
} else if ist == regex.ist_group_end {
|
|
|
|
buf2.write_string('GROUP_END #:${re.prog[state.pc].group_id} deep:$state.group_index')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[state.pc].rep_max == regex.max_quantifier {
|
|
|
|
buf2.write_string('{${re.prog[state.pc].rep_min},MAX}:${re.prog[state.pc].rep}')
|
2020-01-13 15:30:41 +03:00
|
|
|
} else {
|
2021-05-08 13:32:29 +03:00
|
|
|
buf2.write_string('{${re.prog[state.pc].rep_min},${re.prog[state.pc].rep_max}}:${re.prog[state.pc].rep}')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-12-18 07:57:31 +03:00
|
|
|
if re.prog[state.pc].greedy == true {
|
2021-05-08 13:32:29 +03:00
|
|
|
buf2.write_string('?')
|
2020-01-16 02:39:33 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
buf2.write_string(' (#$state.group_index)')
|
2020-12-18 07:57:31 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if ist == regex.ist_dot_char {
|
|
|
|
buf2.write_string(' last!')
|
2020-12-18 07:57:31 +03:00
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
buf2.write_string('\n')
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-04-25 23:42:48 +03:00
|
|
|
sss2 := buf2.str()
|
2021-05-08 13:32:29 +03:00
|
|
|
re.log_func(sss2)
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
}
|
|
|
|
step_count++
|
|
|
|
dbg_line++
|
|
|
|
}
|
|
|
|
//******************************************
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if ist == regex.ist_prog_end {
|
|
|
|
// println("HERE we end!")
|
2020-12-05 03:51:48 +03:00
|
|
|
break
|
|
|
|
}
|
2020-12-18 07:57:31 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// we're out of text, manage it
|
2021-04-15 10:46:49 +03:00
|
|
|
if state.i >= in_txt_len || m_state == .new_line {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Finished text!!")
|
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
|
2020-12-18 07:57:31 +03:00
|
|
|
if state.group_index >= 0 && state.match_index >= 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("End text with open groups!")
|
2020-01-13 15:30:41 +03:00
|
|
|
// close the groups
|
2020-12-18 07:57:31 +03:00
|
|
|
for state.group_index >= 0 {
|
2020-12-22 23:34:46 +03:00
|
|
|
tmp_pc := re.group_data[state.group_index]
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[tmp_pc].group_rep++
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Closing group $state.group_index {${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
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[tmp_pc].group_rep >= re.prog[tmp_pc].rep_min
|
|
|
|
&& re.prog[tmp_pc].group_id >= 0 {
|
|
|
|
start_i := re.group_stack[state.group_index]
|
|
|
|
re.group_stack[state.group_index] = -1
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
// save group results
|
|
|
|
g_index := re.prog[tmp_pc].group_id * 2
|
2020-01-13 15:30:41 +03:00
|
|
|
if start_i >= 0 {
|
|
|
|
re.groups[g_index] = start_i
|
|
|
|
} else {
|
|
|
|
re.groups[g_index] = 0
|
|
|
|
}
|
2020-12-18 07:57:31 +03:00
|
|
|
// we have fished the text, we must manage out pf bound indexes
|
|
|
|
if state.i >= in_txt_len {
|
2021-05-08 13:32:29 +03:00
|
|
|
state.i = in_txt_len - 1
|
2020-12-18 07:57:31 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
re.groups[g_index + 1] = state.i
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.groups[g_index + 1] >= in_txt_len {
|
|
|
|
// println("clamp group on stop!")
|
|
|
|
re.groups[g_index + 1] = in_txt_len - 1
|
2020-12-13 04:04:53 +03:00
|
|
|
}
|
|
|
|
|
2020-01-25 21:12:23 +03:00
|
|
|
// continuous save, save until we have space
|
2020-12-14 16:02:13 +03:00
|
|
|
re.group_continuous_save(g_index)
|
2021-05-08 13:32:29 +03:00
|
|
|
}
|
2020-12-18 07:57:31 +03:00
|
|
|
state.group_index--
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
// the text is finished and the groups closed and we are the last group, ok exit
|
2021-05-08 13:32:29 +03:00
|
|
|
if ist == regex.ist_group_end && re.prog[state.pc + 1].ist == regex.ist_prog_end {
|
|
|
|
// println("Last group end")
|
2020-12-18 07:57:31 +03:00
|
|
|
return state.first_match, state.i
|
|
|
|
}
|
|
|
|
|
|
|
|
if state.pc == -1 {
|
|
|
|
state.pc = last_fnd_pc
|
2020-12-05 03:51:48 +03:00
|
|
|
}
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Finished text!!")
|
|
|
|
// println("Instruction: ${ist:08x} pc: $state.pc")
|
|
|
|
// println("min_rep: ${re.prog[state.pc].rep_min} max_rep: ${re.prog[state.pc].rep_max} rep: ${re.prog[state.pc].rep}")
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2020-12-05 03:51:48 +03:00
|
|
|
// program end
|
2021-05-08 13:32:29 +03:00
|
|
|
if ist == regex.ist_prog_end {
|
|
|
|
// println("Program end on end of text!")
|
2020-12-18 07:57:31 +03:00
|
|
|
return state.first_match, state.i
|
|
|
|
}
|
|
|
|
|
|
|
|
// we are in a last dot_ char case
|
2021-05-08 13:32:29 +03:00
|
|
|
if l_ist == regex.ist_dot_char {
|
|
|
|
// println("***** We have a last dot_char")
|
|
|
|
// println("PC: ${state.pc} last_dot_flag:${re.prog[state.pc].last_dot_flag}")
|
|
|
|
// println("rep: ${re.prog[state.pc].group_rep} min: ${re.prog[state.pc].rep_min} max: ${re.prog[state.pc].rep_max}")
|
|
|
|
// println("first match: ${state.first_match}")
|
|
|
|
if re.prog[state.pc].last_dot_flag == true
|
|
|
|
&& re.prog[state.pc].rep >= re.prog[state.pc].rep_min
|
|
|
|
&& re.prog[state.pc].rep <= re.prog[state.pc].rep_max {
|
2020-12-18 07:57:31 +03:00
|
|
|
return state.first_match, state.i
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Not fitted!!")
|
2020-12-13 04:04:53 +03:00
|
|
|
}
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
// m_state = .end
|
|
|
|
// break
|
2021-09-06 03:11:38 +03:00
|
|
|
|
|
|
|
// no groups open, check the last token quantifier
|
|
|
|
if ist != regex.ist_group_end && re.prog[state.pc + 1].ist == regex.ist_prog_end {
|
|
|
|
if re.prog[state.pc].rep >= re.prog[state.pc].rep_min
|
|
|
|
&& re.prog[state.pc].rep <= re.prog[state.pc].rep_max {
|
|
|
|
// println("We are in good repetition")
|
|
|
|
return state.first_match, state.i
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// print("No good exit!!")
|
2021-05-08 13:32:29 +03:00
|
|
|
return regex.no_match_found, 0
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
// starting and init
|
|
|
|
if m_state == .start {
|
2020-12-18 07:57:31 +03:00
|
|
|
state.pc = -1
|
2021-05-08 13:32:29 +03:00
|
|
|
state.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
|
2020-12-22 19:42:32 +03:00
|
|
|
else if m_state == .ist_next {
|
2020-12-18 07:57:31 +03:00
|
|
|
state.pc = state.pc + 1
|
|
|
|
re.prog[state.pc].reset()
|
2020-01-13 15:30:41 +03:00
|
|
|
// check if we are in the program bounds
|
2020-12-18 07:57:31 +03:00
|
|
|
if state.pc < 0 || state.pc > re.prog.len {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("ERROR!! PC overflow!!")
|
|
|
|
return regex.err_internal_error, state.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
|
2020-12-22 19:42:32 +03:00
|
|
|
else if m_state == .ist_next_ks {
|
2020-12-18 07:57:31 +03:00
|
|
|
state.pc = state.pc + 1
|
2020-01-13 15:30:41 +03:00
|
|
|
// check if we are in the program bounds
|
2020-12-18 07:57:31 +03:00
|
|
|
if state.pc < 0 || state.pc > re.prog.len {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("ERROR!! PC overflow!!")
|
|
|
|
return regex.err_internal_error, state.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
|
2020-12-18 07:57:31 +03:00
|
|
|
ch, char_len = re.get_charb(in_txt, state.i)
|
2020-01-16 02:39:33 +03:00
|
|
|
|
2020-05-22 00:33:51 +03:00
|
|
|
// check new line if flag f_nl enabled
|
2021-05-08 13:32:29 +03:00
|
|
|
if (re.flag & regex.f_nl) != 0 && char_len == 1 && byte(ch) in regex.new_line_list {
|
2020-01-16 02:39:33 +03:00
|
|
|
m_state = .new_line
|
|
|
|
continue
|
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
// check if stop
|
2020-12-22 19:42:32 +03:00
|
|
|
else if m_state == .stop {
|
2020-01-31 04:29:54 +03:00
|
|
|
// we are in search mode, don't exit until the end
|
2021-05-08 13:32:29 +03:00
|
|
|
if ((re.flag & regex.f_src) != 0) && (ist != regex.ist_prog_end) {
|
2020-12-18 07:57:31 +03:00
|
|
|
last_fnd_pc = state.pc
|
|
|
|
state.pc = -1
|
|
|
|
state.i += char_len
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2020-01-31 04:29:54 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
re.reset_src()
|
|
|
|
state.match_index = -1
|
2020-12-18 07:57:31 +03:00
|
|
|
state.first_match = -1
|
2021-07-14 22:20:05 +03:00
|
|
|
|
|
|
|
// reset state list
|
|
|
|
re.reset()
|
|
|
|
|
2020-01-31 04:29:54 +03:00
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if ist == regex.ist_prog_end {
|
2020-12-18 07:57:31 +03:00
|
|
|
return state.first_match, state.i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
// manage here dot char
|
|
|
|
|
2020-12-22 23:34:46 +03:00
|
|
|
if re.state_list.len > 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Here we are, with stop: state buffer: [${re.state_list.len}]")
|
2020-12-22 23:34:46 +03:00
|
|
|
state = re.state_list.pop()
|
2020-12-18 07:57:31 +03:00
|
|
|
|
|
|
|
state.match_flag = true
|
2021-05-08 13:32:29 +03:00
|
|
|
l_ist = u32(regex.ist_dot_char)
|
2020-12-18 07:57:31 +03:00
|
|
|
|
|
|
|
if state.first_match < 0 {
|
|
|
|
state.first_match = state.i
|
|
|
|
}
|
|
|
|
state.match_index = state.i
|
|
|
|
re.prog[state.pc].rep++ // increase repetitions
|
|
|
|
|
|
|
|
state.i += char_len
|
|
|
|
m_state = .ist_quant_p
|
|
|
|
continue
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// exit on no match
|
2021-05-08 13:32:29 +03:00
|
|
|
return result, 0
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
// ist_load
|
2020-12-22 19:42:32 +03:00
|
|
|
else if m_state == .ist_load {
|
2020-01-13 15:30:41 +03:00
|
|
|
// program end
|
2021-05-08 13:32:29 +03:00
|
|
|
if ist == regex.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
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
if state.group_index >= 0 && state.match_index >= 0 {
|
|
|
|
state.group_index = -1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-01-18 09:38:00 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .stop
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
// check GROUP start, no quantifier is checkd for this token!!
|
2021-05-08 13:32:29 +03:00
|
|
|
else if ist == regex.ist_group_start {
|
2020-12-18 07:57:31 +03:00
|
|
|
state.group_index++
|
2021-05-08 13:32:29 +03:00
|
|
|
re.group_data[state.group_index] = re.prog[state.pc].goto_pc // save where is ist_group_end, we will use it for escape
|
|
|
|
re.group_stack[state.group_index] = state.i // index where we start to manage
|
|
|
|
// println("group_index $state.group_index rep ${re.prog[re.prog[state.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
|
2021-05-08 13:32:29 +03:00
|
|
|
else if ist == regex.ist_group_end {
|
2020-01-13 15:30:41 +03:00
|
|
|
// we are in matching streak
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Group END!! last ist: ${l_ist:08x}")
|
2020-01-13 15:30:41 +03:00
|
|
|
if state.match_index >= 0 {
|
|
|
|
// restore txt index stack and save the group data
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("g.id: ${re.prog[state.pc].group_id} group_index: ${state.group_index}")
|
2020-12-18 07:57:31 +03:00
|
|
|
if state.group_index >= 0 && re.prog[state.pc].group_id >= 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
start_i := re.group_stack[state.group_index]
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
// save group results
|
|
|
|
g_index := re.prog[state.pc].group_id * 2
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
if start_i >= 0 {
|
|
|
|
re.groups[g_index] = start_i
|
|
|
|
} else {
|
|
|
|
re.groups[g_index] = 0
|
|
|
|
}
|
2020-12-18 07:57:31 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
re.groups[g_index + 1] = state.i
|
2020-12-18 07:57:31 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if g_index > 0 && re.groups[g_index] <= re.groups[g_index - 1] {
|
|
|
|
re.groups[g_index] = re.groups[g_index - 1]
|
2020-12-21 07:36:14 +03:00
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.groups[g_index + 1] >= in_txt_len {
|
|
|
|
// println("clamp group!")
|
|
|
|
re.groups[g_index + 1] = in_txt_len - 1
|
2020-12-13 04:04:53 +03:00
|
|
|
}
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("GROUP ${re.prog[state.pc].group_id} END [${re.groups[g_index]}, ${re.groups[g_index+1]}] i: $state.i in_txt_len: $in_txt_len")
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2020-01-25 21:12:23 +03:00
|
|
|
// continuous save, save until we have space
|
2020-12-14 16:02:13 +03:00
|
|
|
re.group_continuous_save(g_index)
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
re.prog[state.pc].group_rep++ // increase repetitions
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("GROUP $group_index END ${re.prog[state.pc].group_rep}")
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_quant_pg
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
m_state = .ist_quant_ng
|
2020-04-23 02:16:16 +03:00
|
|
|
continue
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
// check OR
|
2021-05-08 13:32:29 +03:00
|
|
|
else if ist == regex.ist_or_branch {
|
2020-01-13 15:30:41 +03:00
|
|
|
if state.match_index >= 0 {
|
2020-12-18 07:57:31 +03:00
|
|
|
state.pc = re.prog[state.pc].rep_max
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("ist_or_branch True pc: $state.pc")
|
|
|
|
} else {
|
2020-12-18 07:57:31 +03:00
|
|
|
state.pc = re.prog[state.pc].rep_min
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("ist_or_branch False pc: $state.pc")
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-12-18 07:57:31 +03:00
|
|
|
re.prog[state.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
|
2021-05-08 13:32:29 +03:00
|
|
|
else if ist == regex.ist_dot_char {
|
|
|
|
// println("ist_dot_char rep: ${re.prog[state.pc].rep}")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
// check next token to be false
|
|
|
|
mut next_check_flag := false
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
// if we are done with max go on dot char are dedicated case!!
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[state.pc].rep >= re.prog[state.pc].rep_max {
|
2020-12-22 23:34:46 +03:00
|
|
|
re.state_list.pop()
|
2020-12-18 07:57:31 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[state.pc].dot_check_pc >= 0
|
|
|
|
&& re.prog[state.pc].rep >= re.prog[state.pc].rep_min {
|
2020-12-18 07:57:31 +03:00
|
|
|
// load the char
|
2021-05-08 13:32:29 +03:00
|
|
|
// ch_t, _ := re.get_charb(in_txt, state.i+char_len)
|
2020-12-18 07:57:31 +03:00
|
|
|
ch_t := ch
|
|
|
|
chk_pc := re.prog[state.pc].dot_check_pc
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
// simple char
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[chk_pc].ist == regex.ist_simple_char {
|
2020-12-18 07:57:31 +03:00
|
|
|
if re.prog[chk_pc].ch == ch_t {
|
|
|
|
next_check_flag = true
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Check [ist_simple_char] [${re.prog[chk_pc].ch}]==[${ch_t:c}] => $next_check_flag")
|
2020-12-18 07:57:31 +03:00
|
|
|
}
|
2021-01-18 15:20:06 +03:00
|
|
|
// char char_class
|
2021-05-08 13:32:29 +03:00
|
|
|
else if re.prog[chk_pc].ist == regex.ist_char_class_pos
|
|
|
|
|| re.prog[chk_pc].ist == regex.ist_char_class_neg {
|
2020-12-18 07:57:31 +03:00
|
|
|
mut cc_neg := false
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[chk_pc].ist == regex.ist_char_class_neg {
|
2020-12-18 07:57:31 +03:00
|
|
|
cc_neg = true
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
mut cc_res := re.check_char_class(chk_pc, ch_t)
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
if cc_neg {
|
|
|
|
cc_res = !cc_res
|
|
|
|
}
|
|
|
|
next_check_flag = cc_res
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Check [ist_char_class] => $next_check_flag")
|
2020-01-18 09:38:00 +03:00
|
|
|
}
|
2020-12-18 07:57:31 +03:00
|
|
|
// check bsls
|
2021-05-08 13:32:29 +03:00
|
|
|
else if re.prog[chk_pc].ist == regex.ist_bsls_char {
|
2020-12-18 07:57:31 +03:00
|
|
|
next_check_flag = re.prog[chk_pc].validator(byte(ch_t))
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Check [ist_bsls_char] => $next_check_flag")
|
2020-12-18 07:57:31 +03:00
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
}
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
// check if we must continue or pass to the next IST
|
2021-05-08 13:32:29 +03:00
|
|
|
if next_check_flag == true && re.prog[state.pc + 1].ist != regex.ist_prog_end {
|
|
|
|
// println("save the state!!")
|
|
|
|
mut dot_state := StateObj{
|
2020-12-18 07:57:31 +03:00
|
|
|
group_index: state.group_index
|
2021-05-08 13:32:29 +03:00
|
|
|
match_flag: state.match_flag
|
2020-12-18 07:57:31 +03:00
|
|
|
match_index: state.match_index
|
|
|
|
first_match: state.first_match
|
2021-05-08 13:32:29 +03:00
|
|
|
pc: state.pc
|
|
|
|
i: state.i + char_len
|
|
|
|
char_len: char_len
|
2020-12-18 07:57:31 +03:00
|
|
|
last_dot_pc: state.pc
|
|
|
|
}
|
2021-01-03 03:33:34 +03:00
|
|
|
// if we are mananging a .* stay on the same char on return
|
|
|
|
if re.prog[state.pc].rep_min == 0 {
|
|
|
|
dot_state.i -= char_len
|
|
|
|
}
|
|
|
|
|
|
|
|
re.state_list << dot_state
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
m_state = .ist_quant_n
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("dot_char stack len: ${re.state_list.len}")
|
2020-12-05 03:51:48 +03:00
|
|
|
continue
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-12-13 04:04:53 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
state.match_flag = true
|
2021-05-08 13:32:29 +03:00
|
|
|
l_ist = u32(regex.ist_dot_char)
|
2020-12-18 07:57:31 +03:00
|
|
|
|
|
|
|
if state.first_match < 0 {
|
|
|
|
state.first_match = state.i
|
|
|
|
}
|
|
|
|
state.match_index = state.i
|
|
|
|
re.prog[state.pc].rep++ // increase repetitions
|
|
|
|
|
|
|
|
state.i += char_len
|
|
|
|
m_state = .ist_quant_p
|
2020-01-18 09:38:00 +03:00
|
|
|
continue
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
// char class IST
|
2021-05-08 13:32:29 +03:00
|
|
|
else if ist == regex.ist_char_class_pos || ist == regex.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
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if ist == regex.ist_char_class_neg {
|
2020-01-13 15:30:41 +03:00
|
|
|
cc_neg = true
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
mut cc_res := re.check_char_class(state.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
|
2021-05-08 13:32:29 +03:00
|
|
|
l_ist = u32(regex.ist_char_class_pos)
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
if state.first_match < 0 {
|
|
|
|
state.first_match = state.i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
state.match_index = state.i
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
re.prog[state.pc].rep++ // increase repetitions
|
|
|
|
state.i += char_len // next char
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_quant_p
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
m_state = .ist_quant_n
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
// check bsls
|
2021-05-08 13:32:29 +03:00
|
|
|
else if ist == regex.ist_bsls_char {
|
2020-01-13 15:30:41 +03:00
|
|
|
state.match_flag = false
|
2020-12-18 07:57:31 +03:00
|
|
|
tmp_res := re.prog[state.pc].validator(byte(ch))
|
2021-05-08 13:32:29 +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
|
2021-05-08 13:32:29 +03:00
|
|
|
l_ist = u32(regex.ist_bsls_char)
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
if state.first_match < 0 {
|
|
|
|
state.first_match = state.i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
state.match_index = state.i
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
re.prog[state.pc].rep++ // increase repetitions
|
|
|
|
state.i += char_len // next char
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_quant_p
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
m_state = .ist_quant_n
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
// simple char IST
|
2021-05-08 13:32:29 +03:00
|
|
|
else if ist == regex.ist_simple_char {
|
|
|
|
// println("ist_simple_char")
|
2020-01-13 15:30:41 +03:00
|
|
|
state.match_flag = false
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[state.pc].ch == ch {
|
2020-01-13 15:30:41 +03:00
|
|
|
state.match_flag = true
|
2021-05-08 13:32:29 +03:00
|
|
|
l_ist = regex.ist_simple_char
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
if state.first_match < 0 {
|
|
|
|
state.first_match = state.i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("state.match_index: ${state.match_index}")
|
2020-12-18 07:57:31 +03:00
|
|
|
state.match_index = state.i
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
re.prog[state.pc].rep++ // increase repetitions
|
|
|
|
state.i += char_len // next char
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_quant_p
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
m_state = .ist_quant_n
|
|
|
|
continue
|
2020-04-23 02:16:16 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
// UNREACHABLE
|
|
|
|
// println("PANIC2!! state: $m_state")
|
|
|
|
return regex.err_internal_error, state.i
|
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
|
2020-12-22 19:42:32 +03:00
|
|
|
else if m_state == .ist_quant_ng {
|
2020-01-13 15:30:41 +03:00
|
|
|
// we are finished here
|
2020-12-18 07:57:31 +03:00
|
|
|
if state.group_index < 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Early stop!")
|
|
|
|
result = regex.no_match_found
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .stop
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
tmp_pc := re.group_data[state.group_index] // PC to the end of the group token
|
|
|
|
rep := re.prog[tmp_pc].group_rep // use a temp variable
|
|
|
|
re.prog[tmp_pc].group_rep = 0 // clear the repetitions
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2021-05-08 13:32:29 +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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("ist_quant_ng GROUP CLOSED OK group_index: $state.group_index")
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-12-22 23:34:46 +03:00
|
|
|
state.i = re.group_stack[state.group_index]
|
2020-12-18 07:57:31 +03:00
|
|
|
state.pc = tmp_pc
|
|
|
|
state.group_index--
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
2021-05-08 13:32:29 +03:00
|
|
|
} else if re.prog[tmp_pc].next_is_or {
|
|
|
|
// println("ist_quant_ng OR Negative branch")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2020-12-22 23:34:46 +03:00
|
|
|
state.i = re.group_stack[state.group_index]
|
2021-05-08 13:32:29 +03:00
|
|
|
state.pc = re.prog[tmp_pc + 1].rep_min - 1
|
2020-12-18 07:57:31 +03:00
|
|
|
state.group_index--
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
2021-05-08 13:32:29 +03:00
|
|
|
} else if rep > 0 && rep < re.prog[tmp_pc].rep_min {
|
|
|
|
// println("ist_quant_ng UNDER THE MINIMUM g.i: $state.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
|
2021-05-08 13:32:29 +03:00
|
|
|
if state.group_index > 0 {
|
2020-12-18 07:57:31 +03:00
|
|
|
state.group_index--
|
|
|
|
state.pc = tmp_pc
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_quant_ng //.ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
if state.group_index == 0 {
|
|
|
|
state.group_index--
|
|
|
|
state.pc = tmp_pc // TEST
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
result = regex.no_match_found
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .stop
|
|
|
|
continue
|
2021-05-08 13:32:29 +03:00
|
|
|
} else if rep == 0 && rep < re.prog[tmp_pc].rep_min {
|
|
|
|
// println("ist_quant_ng c_zero UNDER THE MINIMUM g.i: $state.group_index")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if state.group_index > 0 {
|
2020-12-18 07:57:31 +03:00
|
|
|
state.group_index--
|
|
|
|
state.pc = tmp_pc
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_quant_ng //.ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
result = regex.no_match_found
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .stop
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("DO NOT STAY HERE!! {${re.prog[tmp_pc].rep_min},${re.prog[tmp_pc].rep_max}}:$rep")
|
|
|
|
// UNREACHABLE
|
|
|
|
return regex.err_internal_error, state.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
|
2021-01-18 15:20:06 +03:00
|
|
|
else if m_state == .ist_quant_pg {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println(".ist_quant_pg")
|
2020-12-18 07:57:31 +03:00
|
|
|
mut tmp_pc := state.pc
|
|
|
|
if state.group_index >= 0 {
|
2020-12-22 23:34:46 +03:00
|
|
|
tmp_pc = re.group_data[state.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 {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("ist_quant_pg UNDER RANGE")
|
2020-12-18 07:57:31 +03:00
|
|
|
state.pc = re.prog[tmp_pc].goto_pc
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
2021-05-08 13:32:29 +03:00
|
|
|
} else if rep == re.prog[tmp_pc].rep_max {
|
|
|
|
// println("ist_quant_pg MAX RANGE")
|
2020-01-13 15:30:41 +03:00
|
|
|
re.prog[tmp_pc].group_rep = 0 // clear the repetitions
|
2020-12-18 07:57:31 +03:00
|
|
|
state.group_index--
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
continue
|
2021-05-08 13:32:29 +03:00
|
|
|
} else if rep >= re.prog[tmp_pc].rep_min {
|
|
|
|
// println("ist_quant_pg IN RANGE group_index:$state.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
|
2020-12-18 07:57:31 +03:00
|
|
|
state.group_index--
|
2020-01-16 02:39:33 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
state.pc = re.prog[tmp_pc].goto_pc - 1
|
|
|
|
state.group_index--
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
// UNREACHABLE
|
|
|
|
// println("PANIC3!! state: $m_state")
|
|
|
|
return regex.err_internal_error, state.i
|
2020-01-13 15:30:41 +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 {
|
2020-12-18 07:57:31 +03:00
|
|
|
rep := re.prog[state.pc].rep
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Here!! PC $state.pc is_next_or: ${re.prog[state.pc].next_is_or}")
|
2020-01-13 15:30:41 +03:00
|
|
|
|
|
|
|
// zero quantifier * or ?
|
2020-12-18 07:57:31 +03:00
|
|
|
if rep == 0 && re.prog[state.pc].rep_min == 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("ist_quant_n c_zero RANGE MIN")
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next // go to next ist
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
// match + or *
|
2020-12-18 07:57:31 +03:00
|
|
|
else if rep >= re.prog[state.pc].rep_min {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("ist_quant_n MATCH RANGE")
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// check the OR if present
|
2020-12-18 07:57:31 +03:00
|
|
|
if re.prog[state.pc].next_is_or {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("OR present on failing")
|
2020-01-13 15:30:41 +03:00
|
|
|
state.match_index = -1
|
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// we are in a group manage no match from here
|
2020-12-18 07:57:31 +03:00
|
|
|
if state.group_index >= 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("ist_quant_n FAILED insied a GROUP group_index:$state.group_index")
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_quant_ng
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
|
|
|
|
// no other options
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("ist_quant_n no_match_found")
|
|
|
|
result = regex.no_match_found
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .stop
|
|
|
|
continue
|
2021-05-08 13:32:29 +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 {
|
2021-09-06 03:11:38 +03:00
|
|
|
// println("Here .ist_quant_p")
|
2020-01-13 15:30:41 +03:00
|
|
|
// exit on first match
|
2021-05-08 13:32:29 +03:00
|
|
|
if (re.flag & regex.f_efm) != 0 {
|
|
|
|
return state.i, state.i + 1
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2020-12-18 07:57:31 +03:00
|
|
|
rep := re.prog[state.pc].rep
|
2021-09-06 03:11:38 +03:00
|
|
|
// println(rep)
|
2020-04-23 02:16:16 +03:00
|
|
|
|
2020-01-13 15:30:41 +03:00
|
|
|
// under range
|
2020-12-18 07:57:31 +03:00
|
|
|
if rep > 0 && rep < re.prog[state.pc].rep_min {
|
2021-05-08 13:32:29 +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
|
2020-12-18 07:57:31 +03:00
|
|
|
else if rep >= re.prog[state.pc].rep_min && rep < re.prog[state.pc].rep_max {
|
2021-05-08 13:32:29 +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
|
2020-12-18 07:57:31 +03:00
|
|
|
if re.prog[state.pc].greedy == true {
|
2020-01-16 02:39:33 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_load
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
// max reached
|
2020-12-18 07:57:31 +03:00
|
|
|
else if rep == re.prog[state.pc].rep_max {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("ist_quant_p MAX RANGE")
|
2020-01-13 15:30:41 +03:00
|
|
|
m_state = .ist_next
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
// UNREACHABLE
|
|
|
|
// println("PANIC4!! state: $m_state")
|
|
|
|
return regex.err_internal_error, state.i
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Check end of text!")
|
2020-01-13 15:30:41 +03:00
|
|
|
// Check the results
|
|
|
|
if state.match_index >= 0 {
|
2020-12-18 07:57:31 +03:00
|
|
|
if state.group_index < 0 {
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[state.pc].ist == regex.ist_prog_end {
|
|
|
|
// println("program ended!!")
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if (re.flag & regex.f_src) != 0 {
|
|
|
|
// println("find return")
|
2020-12-18 07:57:31 +03:00
|
|
|
return state.first_match, state.i
|
2020-12-05 03:51:48 +03:00
|
|
|
} else {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Here!!")
|
2020-12-18 07:57:31 +03:00
|
|
|
return 0, state.i
|
2020-12-05 03:51:48 +03:00
|
|
|
}
|
|
|
|
}
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("No Group here, natural end [$state.first_match,$state.i] state: ${state_str(m_state)} ist: $ist pgr_end: $re.prog.len")
|
2021-01-18 15:20:06 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
if re.prog[state.pc + 1].ist == regex.ist_prog_end
|
|
|
|
|| re.prog[state.pc].ist == regex.ist_prog_end {
|
2020-12-18 07:57:31 +03:00
|
|
|
rep := re.prog[state.pc].rep
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("rep: $rep re.prog[state.pc].rep_min: ${re.prog[state.pc].rep_min} re.prog[state.pc].rep_max: ${re.prog[state.pc].rep_max}")
|
2020-12-18 07:57:31 +03:00
|
|
|
if rep >= re.prog[state.pc].rep_min && rep <= re.prog[state.pc].rep_max {
|
|
|
|
return state.first_match, state.i
|
2020-12-05 03:51:48 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Program not finished! ")
|
|
|
|
return regex.no_match_found, 0
|
2020-12-05 03:51:48 +03:00
|
|
|
}
|
|
|
|
if src_end {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("program end")
|
2020-12-18 07:57:31 +03:00
|
|
|
return state.first_match, state.i
|
2020-12-05 03:51:48 +03:00
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
// print("No match found!!")
|
|
|
|
return regex.no_match_found, 0
|
2020-01-13 15:30:41 +03:00
|
|
|
} else {
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Group match! OK")
|
|
|
|
// println("first_match: $state.first_match, i: $state.i")
|
2020-12-05 03:51:48 +03:00
|
|
|
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("Skip last group")
|
|
|
|
return state.first_match, state.i
|
|
|
|
// return state.first_match,re.group_stack[state.group_index--]
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|
|
|
|
}
|
2021-05-08 13:32:29 +03:00
|
|
|
// println("no_match_found, natural end")
|
|
|
|
return regex.no_match_found, 0
|
2020-01-13 15:30:41 +03:00
|
|
|
}
|