From 5a1944a06dce38e49830fb7507447b8dbc065596 Mon Sep 17 00:00:00 2001
From: NoPlagiarism <NoPlagiarism@noreply.codeberg.org>
Date: Wed, 17 May 2023 15:07:14 +0500
Subject: [PATCH] Add more comments for regex pattern

---
 main.py | 27 +++++++++++++++++++++++----
 1 file changed, 23 insertions(+), 4 deletions(-)

diff --git a/main.py b/main.py
index 66b3a0c..0891b0f 100644
--- a/main.py
+++ b/main.py
@@ -23,18 +23,37 @@ def from_tuple_to_instance_json(data: tuple) -> dict:  # data in the same order,
 
 
 def get_info_from_readme_iter(url: str):
-    pattern = re.compile(r"\|\s+\[(?P<domain>(?:[^\|]|\\\|)+)\]"  # [example.com] or even [example.com OfFiCiAl] 
+    """Some info about pattern
+
+    TL:DR:
+     - Learn regex - https://github.com/ziishaned/learn-regex/blob/master/README.md
+     - Markdown Cheatsheet - https://github.com/adam-p/markdown-here/wiki/Markdown-Cheatsheet#tables
+     - Regex example on regex101 - https://regex101.com/r/OpcjyY/1
+
+    The basis of the code below is scraping raw .MD table, that has **valid** information
+    Table has 5 columns: | [domain or name](link) | cloudflare (usually "Yes" or "No") | country | isp | branch |
+
+    If we need match `| any information |` we need to match borders, spaces before and after info, so it would be like
+    `\|\s+[(?P<info>(?:[^\|]|\\\|)+)\s+\|`.
+    (?:[^\|]|\\\|)+ - means any character except border of column, excluding escaped character
+
+    Only column regex pattern's checking is [domain](url) (It's md link), specifically "url" part
+    URL must start with "https://" (or "http://") and can't contain ")"
+
+    To escape matching foreign table columns table is being cropped using README_CROP constants
+    """
+    pattern = re.compile(r"\|\s+\[(?P<domain>(?:[^\|]|\\\|)+)\]"  # [example.com] or even [example.com OfFiCiAl]
                          r"\((?P<url>https?:\/\/(?:www\.)?[^\)]+)\)\s+\|"  # (url). Accepts anything like "http://www...grg", no checks
-                         r"\s+(?P<cloudflare>(?:[^\|]|\\\|)+)\s+\|"  # All 4 columns below accepts all symbols except "|", but accepts "\|"
+                         r"\s+(?P<cloudflare>(?:[^\|]|\\\|)+)\s+\|"  # All 4 columns below accepts all symbols except "|", but accepts "\|" (escaped "|" in .MD)
                          r"\s+(?P<country>(?:[^\|]|\\\|)+)\s+\|"
                          r"\s+(?P<isp>(?:[^\|]|\\\|)+)\s+\|"
-                         r"\s+(?P<branch>(?:[^\|]|\\\|)+)\|",
+                         r"\s+(?P<branch>(?:[^\|]|\\\|)+)\s+\|",
                          flags=re.MULTILINE | re.IGNORECASE)
     print("Getting MD")
     r = requests.get(url, headers=HEADERS)
     text = r.text
 
-    # Cropping Instances only
+    # Cropping Instances tables only
     crop_from_index = text.index(README_CROP[0])+len(README_CROP[0]) if README_CROP[0] is not None else 0
     crop_to_index = text[crop_from_index:].index(README_CROP[1]) + crop_from_index if README_CROP[1] is not None else len(text)
     instances_str = text[crop_from_index:crop_to_index]