Detect bare links (#13)

Issue: #11 

Passing links without any tags
```
https://github.com
```

.markdownlint.yaml

@@ -1,7 +1,8 @@
 # Default state for all rules
 default: true
 
+MD003: false  # heading-style
 MD013: false  # Line length
 MD033: false  # Inline HTML
+MD034: false  # no-bare-urls
 MD041: false  # First line
-MD003: false  # heading-style

md_dead_link_check/preprocess.py

@@ -9,6 +9,7 @@
 from git import Repo
 
 RE_HEADER = r"^(?:\s*[-+*]\s+|)[#]{1,6}\s*(.*?)\s*[#]*$"
+RE_URL = r"(http[s]?://[^>)\]\s\"]+)"
 RE_LINK = r"([!]{0,1})\[([^\]!]*)\]\(([^()\s]+(?:\([^()\s]*\))*)\s*(.*?)\)"
 RE_HTML_TAG = r"</?\w+[^>]*>"
 RE_HTML_TAG_ID = r"<\w+\s+(?:[^>]*?\s+)?(?:id|name)=([\"'])(.*?)\1"
@@ -113,16 +114,19 @@ def process_md_file(path: Path, root_dir: Path) -> MarkdownInfo:
             line = re.sub(RE_SUB, "", line)
 
             # Detect links
+            copy_line = line  # Used to detect bare links
             matches = re.findall(RE_LINK, line)
             for img_tag, text, link, title in matches:
                 links.append(LinkInfo(link, path, line_num))
+                copy_line = copy_line.replace(link, "")
 
             if matches:
                 # For case [![text](img_link)](link)
                 sub_line = re.sub(RE_LINK, "link", line)
                 matches2 = re.findall(RE_LINK, sub_line)
                 for img_tag, text, link, title in matches2:
                     links.append(LinkInfo(link, path, line_num))
+                    copy_line = copy_line.replace(link, "")
 
             # Detect id under a tag <a id="introduction"></a>
             matches = re.findall(RE_HTML_TAG_ID, line)
@@ -133,6 +137,14 @@ def process_md_file(path: Path, root_dir: Path) -> MarkdownInfo:
             matches = re.findall(RE_HTML_TAG_HREF, line)
             for _, link in matches:
                 links.append(LinkInfo(link, path, line_num))
+                copy_line = copy_line.replace(link, "")
+
+            # Detect simple urls without any tags
+            matches = re.findall(RE_URL, copy_line)
+            for url in matches:
+                if url.endswith("."):
+                    url = url[:-1]
+                links.append(LinkInfo(url, path, line_num))
     return MarkdownInfo(path=path, fragments=fragments, links=links)
 
 

tests/test_md_files/a.md

@@ -24,9 +24,9 @@ Some text
 
 ## links ##
 
-[github](https://github.com/AlexanderDokuchaev)
+[github](https://github.com/AlexanderDokuchaev) https://github.com
 [b](./b.md) [d.a](b.md) `[A+B](A)`
-<a href="./d/a.md" target="_blank">d.a</a><span href="./d/a.md">d.a</span>
+<a href="./d/a.md" target="_blank">d.a</a><span href="https://github.com">d.a</span>
 [d.a](/tests/test_md_files/d/a.md "tag")
 
 ### Header with `quotes` and $math$
@@ -59,4 +59,4 @@ Some text
 <a href="mailto:[email protected]">mail</a>
 
 [ftp](ftp://example.example/example)
-
+https://github.com.

tests/test_preprocess.py

@@ -72,6 +72,11 @@ def test_process_md_file():
             location=Path("tests/test_md_files/a.md"),
             line_num=27,
         ),
+        LinkInfo(
+            link="https://github.com",
+            location=Path("tests/test_md_files/a.md"),
+            line_num=27,
+        ),
         LinkInfo(
             link="./b.md",
             location=Path("tests/test_md_files/a.md"),
@@ -88,7 +93,7 @@ def test_process_md_file():
             line_num=29,
         ),
         LinkInfo(
-            link="./d/a.md",
+            link="https://github.com",
             location=Path("tests/test_md_files/a.md"),
             line_num=29,
         ),
@@ -157,5 +162,10 @@ def test_process_md_file():
             location=Path("tests/test_md_files/a.md"),
             line_num=61,
         ),
+        LinkInfo(
+            link="https://github.com",
+            location=Path("tests/test_md_files/a.md"),
+            line_num=62,
+        ),
     ]
     assert md_info.links == ref_links