regex: fix compilation issues with gcc under ubuntu (#7112)

pull/7118/head
penguindark 2020-12-03 19:33:53 +01:00 committed by GitHub
parent 793f9ae9e3
commit 15ffce1317
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 86 additions and 90 deletions

View File

@ -92,9 +92,7 @@ fn utf8util_char_len(b byte) int {
fn (re RE) get_char(in_txt string, i int) (u32,int) { fn (re RE) get_char(in_txt string, i int) (u32,int) {
ini := unsafe {in_txt.str[i]} ini := unsafe {in_txt.str[i]}
// ascii 8 bit // ascii 8 bit
if (re.flag & f_bin) !=0 || if (re.flag & f_bin) !=0 || ini & 0x80 == 0 {
ini & 0x80 == 0
{
return u32(ini), 1 return u32(ini), 1
} }
// unicode char // unicode char
@ -112,9 +110,7 @@ fn (re RE) get_char(in_txt string, i int) (u32,int) {
[inline] [inline]
fn (re RE) get_charb(in_txt byteptr, i int) (u32,int) { fn (re RE) get_charb(in_txt byteptr, i int) (u32,int) {
// ascii 8 bit // ascii 8 bit
if (re.flag & f_bin) !=0 || if (re.flag & f_bin) !=0 || unsafe {in_txt[i]} & 0x80 == 0 {
unsafe {in_txt[i]} & 0x80 == 0
{
return u32(unsafe {in_txt[i]}), 1 return u32(unsafe {in_txt[i]}), 1
} }
// unicode char // unicode char
@ -131,11 +127,11 @@ fn (re RE) get_charb(in_txt byteptr, i int) (u32,int) {
[inline] [inline]
fn is_alnum(in_char byte) bool { fn is_alnum(in_char byte) bool {
mut tmp := in_char - `A` mut tmp := in_char - `A`
if tmp >= 0x00 && tmp <= 25 { return true } if tmp <= 25 { return true }
tmp = in_char - `a` tmp = in_char - `a`
if tmp >= 0x00 && tmp <= 25 { return true } if tmp <= 25 { return true }
tmp = in_char - `0` tmp = in_char - `0`
if tmp >= 0x00 && tmp <= 9 { return true } if tmp <= 9 { return true }
if tmp == `_` { return true } if tmp == `_` { return true }
return false return false
} }
@ -158,7 +154,7 @@ fn is_not_space(in_char byte) bool {
[inline] [inline]
fn is_digit(in_char byte) bool { fn is_digit(in_char byte) bool {
tmp := in_char - `0` tmp := in_char - `0`
return tmp <= 0x09 && tmp >= 0 return tmp <= 0x09
} }
[inline] [inline]
@ -179,13 +175,13 @@ fn is_not_wordchar(in_char byte) bool {
[inline] [inline]
fn is_lower(in_char byte) bool { fn is_lower(in_char byte) bool {
tmp := in_char - `a` tmp := in_char - `a`
return tmp >= 0x00 && tmp <= 25 return tmp <= 25
} }
[inline] [inline]
fn is_upper(in_char byte) bool { fn is_upper(in_char byte) bool {
tmp := in_char - `A` tmp := in_char - `A`
return tmp >= 0x00 && tmp <= 25 return tmp <= 25
} }
pub fn (re RE) get_parse_error_string(err int) string { pub fn (re RE) get_parse_error_string(err int) string {
@ -920,7 +916,6 @@ pub fn (mut re RE) compile(in_txt string) (int,int) {
fn (mut re RE) impl_compile(in_txt string) (int,int) { fn (mut re RE) impl_compile(in_txt string) (int,int) {
mut i := 0 // input string index mut i := 0 // input string index
mut pc := 0 // program counter mut pc := 0 // program counter
mut tmp_code := u32(0)
// group management variables // group management variables
mut group_count := -1 mut group_count := -1
@ -932,7 +927,6 @@ fn (mut re RE) impl_compile(in_txt string) (int,int) {
i = 0 i = 0
for i < in_txt.len { for i < in_txt.len {
tmp_code = u32(0)
mut char_tmp := u32(0) mut char_tmp := u32(0)
mut char_len := 0 mut char_len := 0
//println("i: ${i:3d} ch: ${in_txt.str[i]:c}") //println("i: ${i:3d} ch: ${in_txt.str[i]:c}")
@ -1502,8 +1496,10 @@ pub fn (mut re RE) match_base(in_txt byteptr, in_txt_len int ) (int,int) {
mut ist := rune(0) // actual instruction mut ist := rune(0) // actual instruction
mut l_ist :=rune(0) // last matched instruction mut l_ist :=rune(0) // last matched instruction
mut group_stack := [-1].repeat(re.group_max) //mut group_stack := [-1].repeat(re.group_max)
mut group_data := [-1].repeat(re.group_max) //mut group_data := [-1].repeat(re.group_max)
mut group_stack := []int{len: re.group_max, init: -1}
mut group_data := []int{len: re.group_max, init: -1}
mut group_index := -1 // group id used to know how many groups are open mut group_index := -1 // group id used to know how many groups are open
@ -1962,7 +1958,7 @@ pub fn (mut re RE) match_base(in_txt byteptr, in_txt_len int ) (int,int) {
/*********************************** /***********************************
* Quantifier management * Quantifier management
***********************************/ ***********************************/
// ist_quant_ng // ist_quant_ng => quantifier negative test on group
if m_state == .ist_quant_ng { if m_state == .ist_quant_ng {
// we are finished here // we are finished here
@ -2039,7 +2035,7 @@ pub fn (mut re RE) match_base(in_txt byteptr, in_txt_len int ) (int,int) {
return err_internal_error, i return err_internal_error, i
} }
// ist_quant_pg // ist_quant_pg => quantifier positive test on group
else if m_state == .ist_quant_pg { else if m_state == .ist_quant_pg {
//println(".ist_quant_pg") //println(".ist_quant_pg")
mut tmp_pc := pc mut tmp_pc := pc
@ -2084,7 +2080,7 @@ pub fn (mut re RE) match_base(in_txt byteptr, in_txt_len int ) (int,int) {
return err_internal_error, i return err_internal_error, i
} }
// ist_quant_n // ist_quant_n => quantifier negative test on token
else if m_state == .ist_quant_n { else if m_state == .ist_quant_n {
rep := re.prog[pc].rep rep := re.prog[pc].rep
//println("Here!! PC $pc is_next_or: ${re.prog[pc].next_is_or}") //println("Here!! PC $pc is_next_or: ${re.prog[pc].next_is_or}")
@ -2125,7 +2121,7 @@ pub fn (mut re RE) match_base(in_txt byteptr, in_txt_len int ) (int,int) {
//return no_match_found, 0 //return no_match_found, 0
} }
// ist_quant_p // ist_quant_p => quantifier positive test on token
else if m_state == .ist_quant_p { else if m_state == .ist_quant_p {
// exit on first match // exit on first match
if (re.flag & f_efm) != 0 { if (re.flag & f_efm) != 0 {