break down functions into smaller blocks

src/gmirator/generate.py

@@ -22,25 +22,32 @@ def gen_gmi():
     make_footer(GMI_FOOTER, DIR_SOURCE)
     logging.info(" Done!")
 
-def make_index(listing: list[Path]):
+def make_index(list_files: list[Path]):
     logging.info(" Populating gemlog index ...")
-    title, date = "", ""
+    gmi_files = (DIR_SOURCE / "gemlog").rglob(r'*.gmi')
-    files = (DIR_SOURCE / "gemlog").rglob(r'*.gmi')
+    gmi_files = [ \
-    files = [ \
+        file for file in gmi_files \
-            file for file in files \
+        if re.search(r'\d\d\d\d.*\.gmi', file.as_posix()) \
-            if re.search(r'\d\d\d\d.*\.gmi', file.as_posix()) \
     ]
-    articles = ""
+    articles = create_articles_index(gmi_files)
-    for file in files[::-1]:
+    write_index_to_files(list_files, articles)
+
+def create_articles_index(gmi_files: list[Path]):
+    articles = []
+    for file in gmi_files[::-1]:
         title, date = find_title_date(file)
         logging.info(f"   \u2713 {date} {title.strip()}")
-        articles += f"=> /gemlog/{file.stem}.gmi {date} - {title}"
+        articles.append(f"=> /gemlog/{file.stem}.gmi {date} - {title}")
+    return ''.join(articles)
 
-    for path in listing:
+def write_index_to_files(list_files: list, articles: str):
+    separator = "## logs\n"
+    size = len(separator)
+    for path in list_files:
         with open(path, "r+") as file:
-            line = file.readline(9)
+            line = file.readline(size)
-            while line != "## logs\n":
+            while line != separator:
-                line = file.readline(9)
+                line = file.readline(size)
             file.seek(0, 1)
             if not path.match(r"gemlog/index.gmi"):
                 file.write("=> /gemlog/index.gmi all gemlogs here\n")
@@ -93,48 +100,66 @@ def gmi2html(file: str):
     with open(file, 'r') as gemlog:
         contents, title = process_file(gemlog)
     with open(DIR_HELPER / "header-part.html", "r") as header_file:
-        header_content = header_file.read()
+        header = header_file.read()
-        header_content = re.sub("PAGETITLE", f"{title}", header_content)
+        header = re.sub("PAGETITLE", f"{title}", header)
     with open(DIR_HELPER / "footer-part.html", "r") as footer_file:
-        footer_content = footer_file.read()
+        footer = footer_file.read()
 
     with open(new_file_path, "w") as new_file:
-        new_file.write(header_content)
+        new_file.write(header)
         new_file.write(contents)
-        new_file.write(footer_content)
+        new_file.write(footer)
 
 def process_file(ifile: TextIOWrapper):
     in_preformated = False
     in_list = False
-    contents = ""
+    contents = []
     title = ""
     for line in ifile:
         if line == "---\n":
             break
-        elif line[:2] == "# ":
+        elif not title and line[:2] == "# ":
             title = line[2:-1]
 
         newline = line
 
-        if in_preformated:
+        newline, in_preformated, skip = process_preformated(newline, in_preformated)
-            newline, n = re.subn(r'^```.*', "</pre>", newline)
+        if skip:
-            in_preformated = False if n else True
+            contents.append(newline)
-            contents += newline.lstrip()
             continue
-        else:
-            newline, n = re.subn(r'^```.*', "<pre>", newline)
-            if n:
-                in_preformated = True
-                continue
 
-        if re.match(r'^[a-zA-Z]', newline):
-            newline = "<p>" + newline.strip() + "</p>\n"
         newline, in_list = process_list(newline, in_list)
-        newline = re.sub(r'^=> (?P<url>[^ ]*) ?(?P<text>.*)\n', repl_url, newline)
+        newline = make_paragraph(newline)
-        newline = re.sub(r'^(#+) (.*)', repl_heading, newline)
+        newline = process_url(newline)
+        newline = process_heading(newline)
         newline = process_inline(newline)
-        contents += newline
+        contents.append(newline)
-    return contents, title
+    return ''.join(contents), title
+
+def process_url(line: str):
+    return re.sub(r'^=> (?P<url>[^ ]*) ?(?P<text>.*)\n', _repl_url, line)
+
+def process_heading(line: str):
+    return re.sub(r'^(#+) (.*)', _repl_heading, line)
+
+def process_preformated(line: str, in_preformated: bool):
+    skip = False
+    if in_preformated:
+        newline, n = re.subn(r'^```.*', "</pre>", line)
+        in_preformated = False if n else True
+        skip = True
+        newline = newline.lstrip()
+    else:
+        newline, n = re.subn(r'^```.*', "<pre>", line)
+        if n:
+            in_preformated = True
+            skip = True
+    return newline, in_preformated, skip
+
+def make_paragraph(line: str):
+    if re.match(r'(^[a-zA-Z]|^\*\w|^~)', line):
+        line = "<p>" + line.strip() + "</p>\n"
+    return line
 
 def process_list(line: str, in_list: bool):
     try:
@@ -160,13 +185,13 @@ def process_inline(line: str):
         line = re.sub(pattern, repl, line)
     return line
 
-def repl_url(matchobj: re.Match):
+def _repl_url(matchobj: re.Match):
     url, text = matchobj.groupdict().values()
     if not re.findall(r'(http|gemini)', url):
         url = re.sub(r'gmi$', r'html', url)
     return f'<a href="{url}">=> {text if text else url}</a><br>\n'
 
-def repl_heading(matchobj: re.Match):
+def _repl_heading(matchobj: re.Match):
     x = len(matchobj.group(1))
     return f"<h{x}>{matchobj.string.strip()}</h{x}>"
 

tests/test_generate.py

@@ -1,16 +1,24 @@
-import re
 from gmirator.generate import (
-    process_file,
+    make_paragraph,
+    process_heading,
     process_list,
     process_inline,
-    repl_url,
+    process_url
-    repl_heading
 )
 
+############################
+### generate gmi section ###
+############################
 
-def test_process_file():
+def test_make_footer():
     pass
 
+def test_find_title_date():
+    pass
+
+#############################
+### generate html section ###
+#############################
 def test_process_list_legit_item():
     test_str = "* this is a list item"
     assert process_list(test_str, True) == (f"<li>{test_str[2:]}</li>", True)
@@ -31,28 +39,34 @@ def test_process_list_empty_line():
 def test_process_inline():
     assert process_inline("*Hello* ~~world~~!") == "<em>Hello</em> <s>world</s>!"
 
-def test_repl_url_external_gmi_url():
+def test_process_url_external_gmi_url():
     external_url = "=> gemini://domain/gempage.gmi\n"
-    new_url = re.sub(r'^=> (?P<url>[^ ]*) ?(?P<text>.*)\n', repl_url, external_url)
+    new_url = process_url(external_url)
     assert new_url == '<a href="gemini://domain/gempage.gmi">=> gemini://domain/gempage.gmi</a><br>\n'
 
-def test_repl_url_internal_gmi_url():
+def test_process_url_internal_gmi_url():
-    external_url = "=> /gempage.gmi title\n"
+    internal_url = "=> /gempage.gmi title\n"
-    new_url = re.sub(r'^=> (?P<url>[^ ]*) ?(?P<text>.*)\n', repl_url, external_url)
+    new_url = process_url(internal_url)
     assert new_url == '<a href="/gempage.html">=> title</a><br>\n'
 
-def test_repl_heading():
+def test_process_heading():
     line = "# this is h1 title"
-    html_h1 = re.sub(r'^(#+) (.*)', repl_heading, line)
+    html_h1 = process_heading(line)
     line = "## this is h2 title"
-    html_h2 = re.sub(r'^(#+) (.*)', repl_heading, line)
+    html_h2 = process_heading(line)
     line = "### this is h3 title"
-    html_h3 = re.sub(r'^(#+) (.*)', repl_heading, line)
+    html_h3 = process_heading(line)
     assert html_h1 == "<h1># this is h1 title</h1>"
     assert html_h2 == "<h2>## this is h2 title</h2>"
     assert html_h3 == "<h3>### this is h3 title</h3>"
 
-def test_repl_heading_h4():
+def test_process_heading_h4():
     line = "#### this is h4 title"
-    html_h4 = re.sub(r'^(#+) (.*)', repl_heading, line)
+    html_h4 = process_heading(line)
     assert html_h4 == "<h4>#### this is h4 title</h4>"
+
+def test_make_paragraph():
+    line = "hello world!"
+    assert make_paragraph(line) == "<p>hello world!</p>\n"
+    line = "*hello world!*"
+    assert make_paragraph(line) == "<p>*hello world!*</p>\n"