adjusted code to work with markdown blocks, added tests, used formatt…

…er on code (#17)

src/codeblock_parser.py

@@ -7,47 +7,56 @@ class CodeblockParser:
     def parse_text(self, text: str, path: Path) -> list:
         parsed_codeblocks = []
         current_codeblock: ParsedCodeBlock = None
-        
+
         for (line_number, line) in enumerate(text.splitlines()):
             if self.has_codeblock_separator(line):
                 if current_codeblock == None or current_codeblock.is_completed():
                     type = self.parse_codeblock_type(line)
                     headers = self.parse_codeblock_headers(line)
-                    
-                    if type is None or type.lower() != "anki":
+
+                    if not self.has_needed_headers(type, headers):
                         continue
-                    
+
                     current_codeblock = ParsedCodeBlock()
 
                     current_codeblock.begin(line_number + 1, path, type, headers)
                 else:
                     content = text.splitlines()[current_codeblock.start_pos:line_number]
                     content = anki_newline_separator.join(content)
-                    
+
                     current_codeblock.complete(
                         content=content,
                         end_pos=line_number)
-                    
+
                     parsed_codeblocks.append(current_codeblock)
                     current_codeblock = None
-           
+
         return parsed_codeblocks
-
+
+    def has_needed_headers(self, type: str, headers: list[str]) -> bool:
+        if type == "anki":
+            return True
+
+        if type == "markdown" and "anki" in headers:
+            return True
+
+        return False
+
     def has_codeblock_separator(self, line: str):
         return line.lstrip().startswith('```')
-    
+
     def parse_codeblock_type(self, header_line: str):
         tail = header_line.lstrip()[3:]
         if len(tail) > 0:
             return tail.split(' ')[0].rstrip()
-        
+
         return None
 
     def parse_codeblock_headers(self, header_line: str) -> list[str]:
         tail = header_line.lstrip()[3:]
         if len(tail) > 0:
             headers = tail.split(' ')
-            
+
             return headers[1:]
-        
+
         return []

src/test_codeblock_parser.py

@@ -5,103 +5,144 @@
 
 def test_parsing_of_one_codeblock():
     parser = CodeblockParser()
-   
+
     content = '''
-    ```anki 
+    ```anki
         some code
         some more code
     ```
     '''
-    
+
     codeblocks = parser.parse_text(content, None)
-    
+
     assert len(codeblocks) == 1
-    
+
     codeblock: ParsedCodeBlock = codeblocks[0]
-    
+
     assert codeblock.type == "anki"
-
+
+    codeblock_content = split_lines_using_anki_separator(codeblock.content)
+
+    assert len(codeblock_content) == 2
+    assert codeblock_content[0].strip() == "some code"
+    assert codeblock_content[1].strip() == "some more code"
+
+def test_parsing_of_one_markdown_codeblock():
+    parser = CodeblockParser()
+
+    content = '''
+    ```markdown anki
+        some code
+        some more code
+    ```
+    '''
+
+    codeblocks = parser.parse_text(content, None)
+
+    assert len(codeblocks) == 1
+
+    codeblock: ParsedCodeBlock = codeblocks[0]
+
+    assert codeblock.type == "markdown"
+
     codeblock_content = split_lines_using_anki_separator(codeblock.content)
-    
+
     assert len(codeblock_content) == 2
     assert codeblock_content[0].strip() == "some code"
     assert codeblock_content[1].strip() == "some more code"
 
 
+def test_ignoring_of_one_markdown_codeblock_without_anki_annotation():
+    parser = CodeblockParser()
+
+    # note no `anki`
+    content = '''
+    ```markdown
+        some code
+        some more code
+    ```
+    '''
+
+    codeblocks = parser.parse_text(content, None)
+
+    assert len(codeblocks) == 0
+
+
 def test_parsing_of_headers_one_codeblock():
     parser = CodeblockParser()
-   
+
     content = '''
-    ```anki header1:value header2
+    ```markdown anki header1:value header2
         some code
         some more code
     ```
     '''
-    
+
     codeblocks = parser.parse_text(content, None)
-    
+
     assert len(codeblocks) == 1
-    
+
     codeblock: ParsedCodeBlock = codeblocks[0]
-
-    assert codeblock.type == "anki"
-
-    assert len(codeblock.headers) == 2
-    assert codeblock.headers[0] == "header1:value" 
-    assert codeblock.headers[1] == "header2" 
+
+    assert codeblock.type == "markdown"
+
+    assert len(codeblock.headers) == 3
+    assert codeblock.headers[0] == "anki"
+    assert codeblock.headers[1] == "header1:value"
+    assert codeblock.headers[2] == "header2"
 
 def test_parsing_of_multiple_codeblocks():
     parser = CodeblockParser()
-   
+
     content = '''
-    ```anki 
+    ```anki
         some code
         some more code
     ```
-    
+
     some irrelevant text
     some irrelevant text
     some irrelevant text
-    
-    ```anki 
+
+    ```markdown anki
         some code2
         some more code2
     ```
-    
+
     some irrelevant text
     some irrelevant text
-    
-    ```anki 
+
+    ```anki
         some code3
         some more code3
         some more more code3
     ```
     '''
-    
+
     codeblocks = parser.parse_text(content, None)
-    
+
     assert len(codeblocks) == 3
-    
+
     codeblock1: ParsedCodeBlock = codeblocks[0]
     codeblock2: ParsedCodeBlock = codeblocks[1]
     codeblock3: ParsedCodeBlock = codeblocks[2]
-    
+
     assert codeblock1.type == "anki"
-    assert codeblock2.type == "anki"
+    assert codeblock2.type == "markdown"
     assert codeblock3.type == "anki"
-    
+
     codeblock1_content = split_lines_using_anki_separator(codeblock1.content)
     codeblock2_content = split_lines_using_anki_separator(codeblock2.content)
     codeblock3_content = split_lines_using_anki_separator(codeblock3.content)
 
     assert len(codeblock1_content) == 2
     assert codeblock1_content[0].strip() == "some code"
     assert codeblock1_content[1].strip() == "some more code"
-    
+
     assert len(codeblock2_content) == 2
     assert codeblock2_content[0].strip() == "some code2"
     assert codeblock2_content[1].strip() == "some more code2"
-    
+
 
     assert len(codeblock3_content) == 3
     assert codeblock3_content[0].strip() == "some code3"