From a98adbb3a4f13c73ed8f215a5e2b5ec73f0a1533 Mon Sep 17 00:00:00 2001
From: penguindark <57967770+penguindark@users.noreply.github.com>
Date: Mon, 28 Dec 2020 11:43:03 +0100
Subject: [PATCH] regex: fix a bug, update docs, explain the assumptions of the
 `regex` module (#7629)

---
 vlib/regex/README.md    | 17 +++++++++++++++--
 vlib/regex/regex.v      |  3 ++-
 vlib/regex/regex_test.v |  1 +
 3 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/vlib/regex/README.md b/vlib/regex/README.md
index c22ba5a7c7..bdd8755f17 100644
--- a/vlib/regex/README.md
+++ b/vlib/regex/README.md
@@ -2,9 +2,22 @@
 
 [TOC]
 
-## introduction
+## Introduction, differences with PCRE
 
-Write here the introduction... not today!! -_-
+The first thing we must point out is that the **V-Regex module is not PCRE compliant** and
+thus some behaviour will be different.
+This module is born upon the V philosophy to have one way and keep it simple.
+The main differences can be summarized in the following points:
+
+- The basic element **is the token not the sequence of symbols**, the most simple token
+is  simple char.
+
+- `|` **OR operator act on token,** for example `abc|ebc` is not `abc` OR `ebc` it 
+is evaluated like `ab` followed by `c OR e` followed by`bc`, this because the **token is
+the base element** not the sequence of symbols.
+- The **match operation stop at the end of the string** not at the new line chars.
+
+Further information can be found in the other part of this document.
 
 ## Basic assumption
 
diff --git a/vlib/regex/regex.v b/vlib/regex/regex.v
index c6bc1bd83f..1bd81b3bc2 100644
--- a/vlib/regex/regex.v
+++ b/vlib/regex/regex.v
@@ -1960,7 +1960,7 @@ pub fn (mut re RE) match_base(in_txt byteptr, in_txt_len int ) (int,int) {
 					continue
 				}
 				
-				if re.prog[state.pc].dot_check_pc >= 0 {
+				if re.prog[state.pc].dot_check_pc >= 0 && re.prog[state.pc].rep >= re.prog[state.pc].rep_min {
 					// load the char
 					//ch_t, _ := re.get_charb(in_txt, state.i+char_len)
 					ch_t := ch
@@ -2338,6 +2338,7 @@ pub fn (mut re RE) match_base(in_txt byteptr, in_txt_len int ) (int,int) {
 					//println("find return")
 					return state.first_match, state.i
 				} else {
+					//println("Here!!")
 					return 0, state.i
 				}
 			}
diff --git a/vlib/regex/regex_test.v b/vlib/regex/regex_test.v
index ce8dcd03ac..36dd9d3bd1 100644
--- a/vlib/regex/regex_test.v
+++ b/vlib/regex/regex_test.v
@@ -123,6 +123,7 @@ match_test_suite = [
 	TestItem{"accccb deer", r"^a(.*)b d(.+)",0,11},
 	TestItem{"accccb deer", r"^(.*)$",0,11},
 	TestItem{"accccb deer", r"^a(.*)b d(.+)p",-1,0},
+	TestItem{"##.#....#.##.####...#.##", r".{18}[.#]",0,19},
 
 	// test bcksls chars
 	TestItem{"[ an s. s! ]( wi4ki:something )", r"\[.*\]\( *(\w*:*\w+) *\)",0,31},