regex: bug fix in replace using function, added tests (#9381)

pull/9369/head
penguindark 2021-03-20 00:54:12 +01:00 committed by GitHub
parent b0e225ac2d
commit 59f95170b3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 111 additions and 26 deletions

View File

@ -1,4 +1,5 @@
import regex import regex
import rand
/****************************************************************************** /******************************************************************************
* *
@ -288,7 +289,7 @@ find_all_test_suite = [
) )
const ( const (
debug = false // true for debug println debug = true // true for debug println
) )
fn test_regex(){ fn test_regex(){
@ -497,3 +498,35 @@ fn test_regex_func(){
assert false assert false
} }
} }
fn my_repl(re regex.RE, in_txt string, start int, end int) string {
s0 := re.get_group_by_id(in_txt,0)[0..1] + "X"
s1 := re.get_group_by_id(in_txt,1)[0..1] + "X"
s2 := re.get_group_by_id(in_txt,2)[0..1] + "X"
return "${s0}${s1}${s2}"
}
// test regex replace function
fn test_regex_func_replace(){
filler := "E il primo dei tre regni dell'Oltretomba cristiano visitato da Dante nel corso del viaggio, con la guida di Virgilio."
txt := r'"content": "They dont necessarily flag "you will be buying these shares on margin!"", "channel_id"'
query := r'"(content":\s+")(.*)(, "channel_id")'
mut re := regex.regex_opt(query) or { panic(err) }
mut txt1 := ""
mut txt2 := ""
for _ in 0..3 {
rnd := int(10+rand.u32() % 20)
txt1 += txt + filler[0..rnd] + "\n"
txt2 += "cXTX,X" + filler[0..rnd] + "\n"
}
result := re.replace_by_fn(txt1, my_repl)
if debug {
eprintln(result)
eprintln(txt2)
}
assert result == txt2
}

View File

@ -8,6 +8,7 @@ that can be found in the LICENSE file.
*/ */
module regex module regex
import strings
/****************************************************************************** /******************************************************************************
* *
@ -71,7 +72,7 @@ pub fn (re RE) get_group_by_id(in_txt string, group_id int) string {
// get_group_by_id get a group boundaries by its id // get_group_by_id get a group boundaries by its id
pub fn (re RE) get_group_bounds_by_id(group_id int) (int,int) { pub fn (re RE) get_group_bounds_by_id(group_id int) (int,int) {
if group_id < (re.groups.len >> 1) { if group_id < re.group_count {
index := group_id << 1 index := group_id << 1
return re.groups[index], re.groups[index + 1] return re.groups[index], re.groups[index + 1]
} }
@ -146,7 +147,7 @@ pub fn (mut re RE) match_string(in_txt string) (int,int) {
* *
******************************************************************************/ ******************************************************************************/
/* /*
// find internal implementation // find internal implementation HERE for reference do not remove!!
[direct_array_access] [direct_array_access]
fn (mut re RE) find_imp(in_txt string) (int,int) { fn (mut re RE) find_imp(in_txt string) (int,int) {
old_flag := re.flag old_flag := re.flag
@ -169,6 +170,9 @@ fn (mut re RE) find_imp(in_txt string) (int,int) {
// find try to find the first match in the input string // find try to find the first match in the input string
[direct_array_access] [direct_array_access]
pub fn (mut re RE) find(in_txt string) (int,int) { pub fn (mut re RE) find(in_txt string) (int,int) {
//old_flag := re.flag
//re.flag |= f_src // enable search mode
mut i := 0 mut i := 0
for i < in_txt.len { for i < in_txt.len {
//--- speed references --- //--- speed references ---
@ -183,18 +187,59 @@ pub fn (mut re RE) find(in_txt string) (int,int) {
//------------------------ //------------------------
if s >= 0 && e > s { if s >= 0 && e > s {
//println("find match in: ${i+s},${i+e} [${in_txt[i+s..i+e]}]") //println("find match in: ${i+s},${i+e} [${in_txt[i+s..i+e]}]")
//re.flag = old_flag
return i+s, i+e return i+s, i+e
} else { } else {
i++ i++
} }
} }
//re.flag = old_flag
return -1, -1
}
// find try to find the first match in the input string strarting from start index
[direct_array_access]
pub fn (mut re RE) find_from(in_txt string, start int) (int,int) {
old_flag := re.flag
re.flag |= f_src // enable search mode
mut i := start
if i < 0 {
return -1, -1
}
for i < in_txt.len {
//--- speed references ---
mut s := -1
mut e := -1
unsafe {
tmp_str := tos(in_txt.str+i, in_txt.len-i)
s,e = re.match_string(tmp_str)
}
//------------------------
//s,e = re.find_imp(in_txt[i..])
//------------------------
if s >= 0 && e > s {
//println("find match in: ${i+s},${i+e} [${in_txt[i+s..i+e]}]")
re.flag = old_flag
return i+s, i+e
} else {
i++
}
}
re.flag = old_flag
return -1, -1 return -1, -1
} }
// find_all find all the non overlapping occurrences of the match pattern // find_all find all the non overlapping occurrences of the match pattern
[direct_array_access] [direct_array_access]
pub fn (mut re RE) find_all(in_txt string) []int { pub fn (mut re RE) find_all(in_txt string) []int {
//old_flag := re.flag
//re.flag |= f_src // enable search mode
mut i := 0 mut i := 0
mut res := []int{} mut res := []int{}
mut ls := -1 mut ls := -1
@ -222,6 +267,7 @@ pub fn (mut re RE) find_all(in_txt string) []int {
} }
} }
//re.flag = old_flag
return res return res
} }
@ -295,34 +341,40 @@ pub type FnReplace = fn (re RE, in_txt string, start int, end int) string
// replace_by_fn return a string where the matches are replaced with the string from the repl_fn callback function // replace_by_fn return a string where the matches are replaced with the string from the repl_fn callback function
pub fn (mut re RE) replace_by_fn(in_txt string, repl_fn FnReplace) string { pub fn (mut re RE) replace_by_fn(in_txt string, repl_fn FnReplace) string {
mut i := 0 mut i := 0
mut res := "" mut res := strings.new_builder(in_txt.len)
mut ls := -1 mut last_end := 0
mut s1 := 0
for i < in_txt.len { for i < in_txt.len {
s,e := re.find(in_txt[i..]) //println("Find Start. $i [${in_txt[i..]}]")
if s >= 0 && e > s && i+s > ls { s, e := re.find_from(in_txt,i)
//println("find match in: ${i+s},${i+e} [${in_txt[i+s..i+e]}] ls:$ls") //println("Find End.")
start := i + s if s >= 0 && e > s {
end := i + e //println("find match in: ${s},${e} [${in_txt[s..e]}]")
// update grups index diplacement
mut gi := 0 if last_end < s {
for gi < re.groups.len { res.write_string(in_txt[last_end..s])
re.groups[gi] += i
gi++
} }
repl := repl_fn(re, in_txt, start, end)
res += in_txt[s1..start] + repl for g_i in 0..re.group_count {
s1 = end re.groups[g_i << 1 ] += i
re.groups[(g_i << 1) + 1] += i
ls = i + s }
i = i + e
continue repl := repl_fn(re, in_txt, s, e)
//println("repl res: $repl")
res.write_string(repl)
//res.write_string("[[${in_txt[s..e]}]]")
last_end = e
i = e
} else { } else {
i++ break
//i++
} }
//println(i)
} }
res += in_txt[s1..] if last_end >= 0 && last_end < in_txt.len {
return res res.write_string(in_txt[last_end..])
}
return res.str()
} }