regex: refactoring, documentation, examples (#7418)

pull/7424/head
penguindark 2020-12-20 04:52:02 +01:00 committed by GitHub
parent 8278af4ee8
commit b29bcb3fbe
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 279 additions and 158 deletions

View File

@ -471,10 +471,23 @@ pub fn regex_opt(in_query string) ?RE
// new_regex create a REgex of small size, usually sufficient for ordinary use
pub fn new() RE
// new_regex_by_size create a REgex of large size, mult specify the scale factor of the memory that will be allocated
pub fn new_by_size(mult int) RE
```
After a base initializer is used, the regex expression must be compiled with:
#### **Custom initialization**
For some particular need it is possible initialize a fully customized regex:
```v ignore
// init custom regex
mut re := regex.RE{}
re.prog = []Token {len: pattern.len + 1} // max program length, can not be longer then the pattern
re.cc = []CharClass{len: pattern.len} // can not be more char class the the length of the pattern
re.group_csave_flag = false // true enable continuos group saving if needed
re.group_max_nested = 128 // set max 128 group nested possible
re.group_max = pattern.len>>1 // we can't have more groups than the half of the pattern legth
```
### Compiling
After an initializer is used, the regex expression must be compiled with:
```v ignore
// compile compiles the REgex returning an error if the compilation fails
pub fn (re mut RE) compile_opt(in_txt string) ?
@ -500,11 +513,38 @@ pub fn (re mut RE) replace(in_txt string, repl string) string
## Find and Replace
There are the following find and replace functions:
#### Find functions
```v ignore
// find try to find the first match in the input string, return start and end index if found else start is -1
pub fn (re mut RE) find(in_txt string) (int,int)
// find_all find all the "non overlapping" occurrences of the matching pattern
// return a list of start end indexes like: [3,4,6,8]
// the matches are [3,4] and [6,8]
pub fn (re mut RE) find_all(in_txt string) []int
```
#### Replace functions
```v ignore
// replace return a string where the matches are replaced with the replace string, only non overlapped matches are used
pub fn (re mut RE) replace(in_txt string, repl string) string
```
#### Custom replace function
For complex find and replace operations it is available the function `replace_by_fn` .
The`replace_by_fn` use a custom replace function making possible customizations.
**The custom function is called for every non overlapped find.**
The custom function must be of the type:
```v ignore
// re RE struct
// in_txt all the text passed to the regex expression
// the match is: in_txt[start..end]
fn (re RE, in_txt string, start int, end int) string
```
@ -671,7 +711,7 @@ re.log_func = custom_print
## Example code
Here there is a simple code to perform some basically match of strings
Here an example that perform some basically match of strings
```v ignore
import regex
@ -698,5 +738,63 @@ fn main(){
}
}
```
Here an example of total customization of the regex environment creation:
```v ignore
import regex
more example code is available in the test code for the `regex` module `vlib\regex\regex_test.v`.
fn main(){
txt := "today John is gone to his house with Jack and Marie."
query := r"(?:(?P<word>\A\w+)|(?:\a\w+)[\s.]?)+"
// init regex
mut re := regex.RE{}
re.prog = []regex.Token {len: query.len + 1} // max program length, can not be longer then the query
re.cc = []regex.CharClass{len: query.len} // can not be more char class the the length of the query
re.prog = []regex.Token {len: query.len+1}
re.group_csave_flag = true // enable continuos group saving
re.group_max_nested = 128 // set max 128 group nested
re.group_max = query.len>>1 // we can't have more groups than the half of the query legth
// compile the query
re.compile_opt(query) or { panic(err) }
start, end := re.match_string(txt)
if start >= 0 {
println("Match ($start, $end) => [${txt[start..end]}]")
} else {
println("No Match")
}
// show results for continuos group saving
if re.group_csave_flag == true && start >= 0 && re.group_csave.len > 0{
println("cg: $re.group_csave")
mut cs_i := 1
for cs_i < re.group_csave[0]*3 {
g_id := re.group_csave[cs_i]
st := re.group_csave[cs_i+1]
en := re.group_csave[cs_i+2]
println("cg[$g_id] $st $en:[${txt[st..en]}]")
cs_i += 3
}
}
// show results for captured groups
if start >= 0 {
println("Match ($start, $end) => [${txt[start..end]}]")
for g_index := 0; g_index < re.group_count ; g_index++ {
println("#${g_index} [${re.get_group_by_id(txt, g_index)}] \
bounds: ${re.get_group_bounds_by_id(g_index)}")
}
for name in re.group_map.keys() {
println("group:'$name' \t=> [${re.get_group_by_name(txt, name)}] \
bounds: ${re.get_group_bounds_by_name(name)}")
}
} else {
println("No Match")
}
}
```
more example code is available in the test code for the `regex` module `vlib\regex\regex_test.v`.

View File

@ -266,11 +266,11 @@ fn (mut tok Token) reset() {
tok.rep = 0
}
/*
Regex struct
*/
/******************************************************************************
*
* Regex struct
*
******************************************************************************/
pub const (
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
@ -354,11 +354,11 @@ fn (mut re RE) reset_src(){
}
}
/*
Backslashes chars
*/
/******************************************************************************
*
* Backslashes chars
*
******************************************************************************/
struct BslsStruct {
ch rune // meta char
validator FnValidator // validator function pointer
@ -430,11 +430,11 @@ fn (re RE) parse_bsls(in_txt string, in_i int) (int,int){
return err_syntax_error, i
}
/*
Char class
*/
/******************************************************************************
*
* Char class
*
******************************************************************************/
const(
cc_null = 0 // empty cc token
cc_char = 1 // simple char: a
@ -653,11 +653,11 @@ fn (mut re RE) parse_char_class(in_txt string, in_i int) (int, int, rune) {
return err_syntax_error,0,u32(0)
}
/*
Re Compiler
*/
/******************************************************************************
*
* Re Compiler
*
******************************************************************************/
//
// Quantifier
//
@ -1462,11 +1462,11 @@ pub fn (re RE) get_query() string {
return res.str()
}
/*
Groups saving utilities
*/
/******************************************************************************
*
* Groups saving utilities
*
******************************************************************************/
[inline]
fn (mut re RE) group_continuous_save(g_index int) {
if re.group_csave_flag == true {
@ -1500,12 +1500,12 @@ fn (mut re RE) group_continuous_save(g_index int) {
re.group_csave << re.groups[g_index+1] // end
}
}
/*
Matching
*/
/******************************************************************************
*
* Matching
*
******************************************************************************/
enum Match_state{
start = 0
stop
@ -2001,6 +2001,7 @@ pub fn (mut re RE) match_base(in_txt byteptr, in_txt_len int ) (int,int) {
last_dot_pc: state.pc
}
m_state = .ist_quant_n
//println("dot_char stack len: $state_list.len")
continue
}
@ -2363,47 +2364,11 @@ pub fn (mut re RE) match_base(in_txt byteptr, in_txt_len int ) (int,int) {
return no_match_found, 0
}
/*
Public functions
*/
//
// Inits
//
// regex create a regex object from the query string
[deprecated]
pub fn regex(in_query string) (RE,int,int){
mut re := RE{}
re.prog = []Token {len: in_query.len+1}
re.cc = []CharClass{len: in_query.len+1}
re.group_max_nested = 8
re_err,err_pos := re.compile(in_query)
return re, re_err, err_pos
}
// new_regex create a RE of small size, usually sufficient for ordinary use
[deprecated]
pub fn new_regex() RE {
return impl_new_regex_by_size(1)
}
// new_regex_by_size create a RE of large size, mult specify the scale factor of the memory that will be allocated
[deprecated]
pub fn new_regex_by_size(mult int) RE {
return impl_new_regex_by_size(mult)
}
fn impl_new_regex_by_size(mult int) RE {
mut re := RE{}
re.prog = []Token {len: max_code_len*mult} // max program length, default 256 istructions
re.cc = []CharClass{len: max_code_len*mult} // char class list
re.group_max_nested = 3*mult // max nested group
return re
}
/******************************************************************************
*
* Public functions
*
******************************************************************************/
//
// Matchers
@ -2538,82 +2503,3 @@ pub fn (mut re RE) replace_by_fn(in_txt string, repl_fn FnReplace) string {
return res
}
/*
Utilities
*/
// get_group_bounds_by_name get a group boundaries by its name
pub fn (re RE) get_group_bounds_by_name(group_name string) (int, int) {
if group_name in re.group_map {
tmp_index := re.group_map[group_name]-1
start := re.groups[tmp_index * 2]
end := re.groups[tmp_index * 2 + 1]
return start,end
}
return -1, -1
}
// get_group_by_name get a group boundaries by its name
pub fn (re RE) get_group_by_name(in_txt string, group_name string) string {
if group_name in re.group_map {
tmp_index := re.group_map[group_name]-1
start := re.groups[tmp_index * 2]
end := re.groups[tmp_index * 2 + 1]
return in_txt[start..end]
}
return ""
}
// get_group_by_id get a group string by its id
pub fn (re RE) get_group_by_id(in_txt string, group_id int) string {
if group_id < (re.groups.len >> 1) {
index := group_id << 1
start := re.groups[index]
end := re.groups[index + 1]
return in_txt[start..end]
}
return ""
}
// 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) {
if group_id < (re.groups.len >> 1) {
index := group_id << 1
return re.groups[index], re.groups[index]
}
return -1, -1
}
pub
struct Re_group {
pub:
start int = -1
end int = -1
}
// get_group_list return a list of Re_group for the found groups
pub fn (re RE) get_group_list() []Re_group {
mut res := []Re_group{len: re.groups.len >> 1}
mut gi := 0
//println("len: ${re.groups.len} groups: ${re.groups}")
for gi < re.groups.len {
if re.groups[gi] >= 0 {
txt_st := re.groups[gi]
txt_en := re.groups[gi+1]
//println("#${gi/2} start: ${re.groups[gi]} end: ${re.groups[gi + 1]} ")
if txt_st >= 0 && txt_en > txt_st {
tmp := Re_group{ start: re.groups[gi], end: re.groups[gi + 1]}
//println(tmp)
res[gi >> 1] = tmp
} else {
res[gi >> 1] = Re_group{}
}
}
gi += 2
}
return res
}

View File

@ -17,18 +17,29 @@ pub fn (mut re RE) compile_opt(pattern string) ? {
}
// new_regex create a RE of small size, usually sufficient for ordinary use
[deprecated]
pub fn new() RE {
return impl_new_regex_by_size(1)
}
// new_regex_by_size create a RE of large size, mult specify the scale factor of the memory that will be allocated
[deprecated]
pub fn new_by_size(mult int) RE {
return impl_new_regex_by_size(mult)
}
// regex_opt create new RE object from RE pattern string
pub fn regex_opt(pattern string) ?RE {
mut re := new()
re.compile_opt(pattern)?
return re
// init regex
mut re := regex.RE{}
re.prog = []Token {len: pattern.len + 1} // max program length, can not be longer then the pattern
re.cc = []CharClass{len: pattern.len} // can not be more char class the the length of the pattern
re.group_csave_flag = false // enable continuos group saving
re.group_max_nested = 128 // set max 128 group nested
re.group_max = pattern.len >> 1 // we can't have more groups than the half of the pattern legth
// compile the pattern
re.compile_opt(pattern)?
return re
}

View File

@ -0,0 +1,126 @@
/*
regex 1.0 alpha
Copyright (c) 2019-2020 Dario Deledda. All rights reserved.
Use of this source code is governed by an MIT license
that can be found in the LICENSE file.
*/
module regex
/******************************************************************************
*
* Inits
*
******************************************************************************/
// regex create a regex object from the query string
[deprecated]
pub fn regex(in_query string) (RE,int,int){
mut re := RE{}
re.prog = []Token {len: in_query.len+1}
re.cc = []CharClass{len: in_query.len+1}
re.group_max_nested = 8
re_err,err_pos := re.compile(in_query)
return re, re_err, err_pos
}
// new_regex create a RE of small size, usually sufficient for ordinary use
[deprecated]
pub fn new_regex() RE {
return impl_new_regex_by_size(1)
}
// new_regex_by_size create a RE of large size, mult specify the scale factor of the memory that will be allocated
[deprecated]
pub fn new_regex_by_size(mult int) RE {
return impl_new_regex_by_size(mult)
}
fn impl_new_regex_by_size(mult int) RE {
mut re := RE{}
re.prog = []Token {len: max_code_len*mult} // max program length, default 256 istructions
re.cc = []CharClass{len: max_code_len*mult} // char class list
re.group_max_nested = 3*mult // max nested group
return re
}
/******************************************************************************
*
* Utilities
*
******************************************************************************/
// get_group_bounds_by_name get a group boundaries by its name
pub fn (re RE) get_group_bounds_by_name(group_name string) (int, int) {
if group_name in re.group_map {
tmp_index := re.group_map[group_name]-1
start := re.groups[tmp_index * 2]
end := re.groups[tmp_index * 2 + 1]
return start,end
}
return -1, -1
}
// get_group_by_name get a group boundaries by its name
pub fn (re RE) get_group_by_name(in_txt string, group_name string) string {
if group_name in re.group_map {
tmp_index := re.group_map[group_name]-1
start := re.groups[tmp_index * 2]
end := re.groups[tmp_index * 2 + 1]
return in_txt[start..end]
}
return ""
}
// get_group_by_id get a group string by its id
pub fn (re RE) get_group_by_id(in_txt string, group_id int) string {
if group_id < (re.groups.len >> 1) {
index := group_id << 1
start := re.groups[index]
end := re.groups[index + 1]
return in_txt[start..end]
}
return ""
}
// 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) {
if group_id < (re.groups.len >> 1) {
index := group_id << 1
return re.groups[index], re.groups[index + 1]
}
return -1, -1
}
pub
struct Re_group {
pub:
start int = -1
end int = -1
}
// get_group_list return a list of Re_group for the found groups
pub fn (re RE) get_group_list() []Re_group {
mut res := []Re_group{len: re.groups.len >> 1}
mut gi := 0
//println("len: ${re.groups.len} groups: ${re.groups}")
for gi < re.groups.len {
if re.groups[gi] >= 0 {
txt_st := re.groups[gi]
txt_en := re.groups[gi+1]
//println("#${gi/2} start: ${re.groups[gi]} end: ${re.groups[gi + 1]} ")
if txt_st >= 0 && txt_en > txt_st {
tmp := Re_group{ start: re.groups[gi], end: re.groups[gi + 1]}
//println(tmp)
res[gi >> 1] = tmp
} else {
res[gi >> 1] = Re_group{}
}
}
gi += 2
}
return res
}