More coherent conf. flags, Updated README, minor code improv.

README.md

@@ -17,11 +17,13 @@ Obviously, it's built with staticoso itself 😁️. Its source repo can be foun
 Keep in mind that, currently, it's still very incomplete. **Any help**, from writing the documentation to creating a decent HTML+CSS template for its site, **is more than welcome**.
 
 ## Dependencies
-- [Python == 3.10.4](https://python.org)
+
+- [Python >= 3.10](https://python.org)
 - (Included) [Python Markdown == 3.3.7](https://pypi.org/project/Markdown)
   - (Included) Third-Party Extensions for Python Markdown: [markdown_del_ins](https://github.com/honzajavorek/markdown-del-ins), [mdx_subscript](https://github.com/jambonrose/markdown_subscript_extension), [mdx_superscript](https://github.com/jambonrose/markdown_superscript_extension)
 - (Included) [Beautiful Soup == 4.11.1](https://pypi.org/project/beautifulsoup4)
 - (Included) [feedgen == 0.9.0](https://pypi.org/project/feedgen)
+  - [lxml == 4.9.1](https://pypi.org/project/lxml)
 - (Included) [htmlmin == 0.1.12](https://pypi.org/project/htmlmin)
 
 ### Optional dependencies
@@ -29,7 +31,7 @@ Keep in mind that, currently, it's still very incomplete. **Any help**, from wri
 Needed for Pug input support:
 
 - [node == 12.22.5](https://nodejs.org) - [npm == 7.5.2](https://www.npmjs.com)
-- (Included) [pug-cli == 1.0.0-alpha6](https://npmjs.com/package/pug-cli)
+- (Included, must be manually installed in system $PATH) [pug-cli == 1.0.0-alpha6](https://npmjs.com/package/pug-cli)
 
 Needed for Gemtext output support:
 
@@ -37,14 +39,17 @@ Needed for Gemtext output support:
 - [html2gmi](https://github.com/LukeEmmet/html2gmi)
 
 ## Features roadmap
+
+- [ ] Overriding internal HTML snippets for template-specific ones
+- [ ] Static syntax highlighing for code blocks in any page
 - [x] File name used as a title for pages without one
 - [ ] Custom category names in header links
 - [ ] Choosing custom name for Blog and Uncategorized categories
 - [ ] Choosing to use a template for all pages in a folder
-- [ ] Configuration with both INI files and CLI arguments
+- [x] Configuration with both INI files and CLI arguments
 - [ ] Category-based feeds
 - [ ] Support for multi-language sites
-- [x] The `title` attribute is added to images which only have `alt` (for desktop accessibility)
+- [x] The `title` attribute is added to images which only have `alt` (for desktop accessibility), or viceversa
 - [x] Local (per-page) and global (per-site) macros
 - [x] ActivityPub (Mastodon) support (Feed + embedded comments)
 - [ ] Polished Gemtext generation
@@ -68,3 +73,9 @@ Needed for Gemtext output support:
 - [x] Auto-detection of titles in a page
 - [x] _HTML_, TXT, _Extended Markdown_, and _Pug_ supported for input page files
 - [ ] Out of heavy-WIP state
+
+## Known issues (might need further investigation)
+
+- Bad HTML included in Markdown files can cause a build to fail entirely.
+- The program currently takes about 2 seconds to build a smallish site. While by itself that's not a long time, problems could arise for bigger sites.
+- Ordering pages in the global menu with external configuration flags (outside the pages' source) yields broken and unpredictable results.

Source/Build.py

@@ -135,14 +135,16 @@ def Main(Args, FeedEntries):
 	ActivityPubTypeFilter = OptionChoose('Post', Args.ActivityPubTypeFilter, ReadConf(SiteConf, 'ActivityPub', 'TypeFilter'))
 	ActivityPubHoursLimit = OptionChoose(168, Args.ActivityPubHoursLimit, ReadConf(SiteConf, 'ActivityPub', 'HoursLimit'))
 	FeedCategoryFilter = OptionChoose('Blog', Args.FeedCategoryFilter, ReadConf(SiteConf, 'Feed', 'CategoryFilter'))
-	Minify = StringBoolChoose(False, Args.Minify, ReadConf(SiteConf, 'Site', 'Minify'))
+	Minify = StringBoolChoose(False, Args.Minify, ReadConf(SiteConf, 'Minify', 'Minify'))
+	MinifyKeepComments = StringBoolChoose(False, Args.MinifyKeepComments, ReadConf(SiteConf, 'Minify', 'KeepComments'))
 	NoScripts = StringBoolChoose(False, Args.NoScripts, ReadConf(SiteConf, 'Site', 'NoScripts'))
 	ImgAltToTitle = StringBoolChoose(True, Args.ImgAltToTitle, ReadConf(SiteConf, 'Site', 'ImgAltToTitle'))
 	ImgTitleToAlt = StringBoolChoose(False, Args.ImgTitleToAlt, ReadConf(SiteConf, 'Site', 'ImgTitleToAlt'))
-	AutoCategories = StringBoolChoose(False, Args.AutoCategories, ReadConf(SiteConf, 'Site', 'AutoCategories'))
+	CategoriesAutomatic = StringBoolChoose(False, Args.CategoriesAutomatic, ReadConf(SiteConf, 'Categories', 'Automatic'))
-	GemtextOut = StringBoolChoose(False, Args.GemtextOut, ReadConf(SiteConf, 'Site', 'GemtextOut'))
+	CategoriesUncategorized = OptionChoose('Uncategorized', Args.CategoriesUncategorized, ReadConf(SiteConf, 'Categories', 'Uncategorized'))
+	GemtextOutput = StringBoolChoose(False, Args.GemtextOutput, ReadConf(SiteConf, 'Gemtext', 'Output'))
 	GemtextHeader = Args.GemtextHeader if Args.GemtextHeader else ReadConf(SiteConf, 'Gemtext', 'Header') if ReadConf(SiteConf, 'Gemtext', 'Header') else f"# {SiteName}\n\n" if SiteName else ''
-	SitemapOut = StringBoolChoose(True, Args.SitemapOut, ReadConf(SiteConf, 'Site', 'SitemapOut'))
+	SitemapOutput = StringBoolChoose(True, Args.SitemapOutput, ReadConf(SiteConf, 'Sitemap', 'Output'))
 	FeedEntries = int(FeedEntries) if (FeedEntries or FeedEntries == 0) and FeedEntries != 'Default' else int(ReadConf(SiteConf, 'Site', 'FeedEntries')) if ReadConf(SiteConf, 'Site', 'FeedEntries') else 10
 	Sorting = literal_eval(OptionChoose('{}', Args.Sorting, ReadConf(SiteConf, 'Site', 'Sorting')))
 
@@ -163,12 +165,12 @@ def Main(Args, FeedEntries):
 	if os.path.isdir('Pages'):
 		HavePages = True
 		shutil.copytree('Pages', OutputDir, dirs_exist_ok=True)
-		if GemtextOut:
+		if GemtextOutput:
 			shutil.copytree('Pages', f"{OutputDir}.gmi", ignore=IgnoreFiles, dirs_exist_ok=True)
 	if os.path.isdir('Posts'):
 		HavePosts = True
 		shutil.copytree('Posts', f"{OutputDir}/Posts", dirs_exist_ok=True)
-		if GemtextOut:
+		if GemtextOutput:
 			shutil.copytree('Posts', f"{OutputDir}.gmi/Posts", ignore=IgnoreFiles, dirs_exist_ok=True)
 
 	if not (HavePages or HavePosts):
@@ -195,11 +197,12 @@ def Main(Args, FeedEntries):
 		SiteLang=SiteLang,
 		Locale=Locale,
 		Minify=Minify,
+		MinifyKeepComments=MinifyKeepComments,
 		NoScripts=NoScripts,
 		ImgAltToTitle=ImgAltToTitle, ImgTitleToAlt=ImgTitleToAlt,
 		Sorting=SetSorting(Sorting),
 		MarkdownExts=MarkdownExts,
-		AutoCategories=AutoCategories)
+		AutoCategories=CategoriesAutomatic)
 
 	if FeedEntries != 0:
 		print("[I] Generating Feeds")
@@ -245,14 +248,14 @@ def Main(Args, FeedEntries):
 		Content = ReplWithEsc(Content, '[staticoso:Comments]', Post)
 		WriteFile(File, Content)
 
-	if GemtextOut:
+	if GemtextOutput:
 		print("[I] Generating Gemtext")
 		GemtextCompileList(OutputDir, Pages, GemtextHeader)
 
 	print("[I] Cleaning Temporary Files")
 	DelTmp(OutputDir)
 
-	if SitemapOut:
+	if SitemapOutput:
 		print("[I] Generating Sitemap")
 		MakeSitemap(OutputDir, Pages, SiteDomain)
 
@@ -261,7 +264,7 @@ def Main(Args, FeedEntries):
 
 if __name__ == '__main__':
 	Parser = argparse.ArgumentParser()
-	Parser.add_argument('--DiffBuild', action='store_true')
+	Parser.add_argument('--DiffBuild', type=str)
 	Parser.add_argument('--OutputDir', type=str)
 	#Parser.add_argument('--InputDir', type=str)
 	Parser.add_argument('--Sorting', type=str)
@@ -272,13 +275,14 @@ if __name__ == '__main__':
 	Parser.add_argument('--SiteTemplate', type=str)
 	Parser.add_argument('--SiteDomain', type=str)
 	Parser.add_argument('--Minify', type=str)
+	Parser.add_argument('--MinifyKeepComments', type=str)
 	Parser.add_argument('--NoScripts', type=str)
 	Parser.add_argument('--ImgAltToTitle', type=str)
 	Parser.add_argument('--ImgTitleToAlt', type=str)
-	Parser.add_argument('--GemtextOut', type=str)
+	Parser.add_argument('--GemtextOutput', type=str)
 	Parser.add_argument('--GemtextHeader', type=str)
 	Parser.add_argument('--SiteTagline', type=str)
-	Parser.add_argument('--SitemapOut', type=str)
+	Parser.add_argument('--SitemapOutput', type=str)
 	Parser.add_argument('--FeedEntries', type=str)
 	Parser.add_argument('--FolderRoots', type=str)
 	Parser.add_argument('--DynamicParts', type=str)
@@ -288,7 +292,8 @@ if __name__ == '__main__':
 	Parser.add_argument('--FeedCategoryFilter', type=str)
 	Parser.add_argument('--ActivityPubTypeFilter', type=str, help=argparse.SUPPRESS)
 	Parser.add_argument('--ActivityPubHoursLimit', type=int)
-	Parser.add_argument('--AutoCategories', type=str)
+	Parser.add_argument('--CategoriesUncategorized', type=str)
+	Parser.add_argument('--CategoriesAutomatic', type=str)
 	Args = Parser.parse_args()
 
 	try:

Source/Modules/Config.py

@@ -37,8 +37,8 @@ def EvalOpt(Opt):
 	else:
 		return None
 
-def OptionChoose(Default, Primary, Secondary):
+def OptionChoose(Default, Primary, Secondary, Tertiary=None):
-	return Primary if Primary != None else Secondary if Secondary != None else Default
+	return Primary if Primary != None else Secondary if Secondary != None else Tertiary if Tertiary != None else Default
 
 def StringBoolChoose(Default, Primary, Secondary):
 	Var = Default

Source/Modules/HTML.py

@@ -9,6 +9,7 @@
 
 import html
 import warnings
+from Libs import htmlmin
 from Libs.bs4 import BeautifulSoup
 from Modules.Utils import *
 
@@ -70,3 +71,15 @@ def SquareFnrefs(HTML): # Different combinations of formatting for Soup .prettif
 			s = t.find('a')
 			s.replace_with(f'[{t}]')
 	return str(Soup.prettify(formatter=None))
+
+def DoMinifyHTML(HTML, KeepComments):
+	return htmlmin.minify(
+		input=HTML,
+		remove_comments=not KeepComments,
+		remove_empty_space=True,
+		remove_all_empty_space=False,
+		reduce_empty_attributes=True,
+		reduce_boolean_attributes=True,
+		remove_optional_attribute_quotes=True,
+		convert_charrefs=True,
+		keep_pre=True)

Source/Modules/Site.py

@@ -8,7 +8,6 @@
 | ================================= """
 
 from datetime import datetime
-from Libs import htmlmin
 from Libs.bs4 import BeautifulSoup
 from Modules.Config import *
 from Modules.HTML import *
@@ -18,6 +17,15 @@ from Modules.Utils import *
 
 HTMLSectionTitleLine = '<h{Index} class="SectionHeading"><span class="SectionLink"><a href="#{DashTitle}"><span>»</span></a> </span><span class="SectionTitle" id="{DashTitle}">{Title}</span></h{Index}>'
 #PugSectionTitleLine = "{Line[:Index]}{Line[Index:Index+2]}.SectionHeading #[span.SectionLink #[a(href='#{DashTitle}') #[span »]] ]#[span#{DashTitle}.SectionTitle {Line[Index+2:]}]"
+CategoryPageTemplate = """\
+// Title: {Name}
+// Type: Page
+// Index: True
+
+# {Name}
+
+<div>[staticoso:Category:{Name}]</div>
+"""
 
 def DashifyTitle(Title, Done=[]):
 	return UndupeStr(DashifyStr(Title.lstrip(' ').rstrip(' ')), Done, '-')
@@ -331,54 +339,50 @@ def PatchHTML(File, HTML, StaticPartsText, DynamicParts, DynamicPartsText, HTMLP
 
 	for e in StaticPartsText:
 		HTML = ReplWithEsc(HTML, f"[staticoso:StaticPart:{e}]", StaticPartsText[e])
-	HTML = ReplWithEsc(HTML, '[staticoso:Site:Menu]', HTMLPagesList)
+	HTML = DictReplWithEsc(
-	HTML = ReplWithEsc(HTML, '[staticoso:Page:Lang]', SiteLang)
+		HTML, {
-	HTML = ReplWithEsc(HTML, '[staticoso:Page:Chapters]', HTMLTitles)
+			'[staticoso:Site:Menu]': HTMLPagesList,
-	HTML = ReplWithEsc(HTML, '[staticoso:Page:Title]', Title)
+			'[staticoso:Page:Lang]': SiteLang,
-	HTML = ReplWithEsc(HTML, '[staticoso:Page:Description]', Description)
+			'[staticoso:Page:Chapters]': HTMLTitles,
-	HTML = ReplWithEsc(HTML, '[staticoso:Page:Image]', Image)
+			'[staticoso:Page:Title]': Title,
-	HTML = ReplWithEsc(HTML, '[staticoso:Page:Path]', PagePath)
+			'[staticoso:Page:Description]': Description,
-	HTML = ReplWithEsc(HTML, '[staticoso:Page:Style]', Meta['Style'])
+			'[staticoso:Page:Image]': Image,
-	HTML = ReplWithEsc(HTML, '[staticoso:Page:Content]', Content)
+			'[staticoso:Page:Path]': PagePath,
-	HTML = ReplWithEsc(HTML, '[staticoso:Page:ContentInfo]', MakeContentHeader(Meta, Locale, MakeCategoryLine(File, Meta)))
+			'[staticoso:Page:Style]': Meta['Style'],
-	HTML = ReplWithEsc(HTML, '[staticoso:BuildTime]', datetime.now().strftime('%Y-%m-%d %H:%M'))
+			'[staticoso:Page:Content]': Content,
-	HTML = ReplWithEsc(HTML, '[staticoso:Site:Name]', SiteName)
+			'[staticoso:Page:ContentInfo]': MakeContentHeader(Meta, Locale, MakeCategoryLine(File, Meta)),
-	HTML = ReplWithEsc(HTML, '[staticoso:Site:AbsoluteRoot]', SiteRoot)
+			'[staticoso:BuildTime]': datetime.now().strftime('%Y-%m-%d %H:%M'),
-	HTML = ReplWithEsc(HTML, '[staticoso:Site:RelativeRoot]', GetPathLevels(PagePath))
+			'[staticoso:Site:Name]': SiteName,
+			'[staticoso:Site:AbsoluteRoot]': SiteRoot,
+			'[staticoso:Site:RelativeRoot]': GetPathLevels(PagePath)
+		})
 	for e in Meta['Macros']:
 		HTML = ReplWithEsc(HTML, f"[:{e}:]", Meta['Macros'][e])
 	for e in FolderRoots:
 		HTML = ReplWithEsc(HTML, f"[staticoso:Folder:{e}:AbsoluteRoot]", FolderRoots[e])
 	for e in Categories:
 		HTML = ReplWithEsc(HTML, f"<span>[staticoso:Category:{e}]</span>", Categories[e])
+		HTML = ReplWithEsc(HTML, f"[staticoso:Category:{e}]", Categories[e])
 
 	# TODO: Clean this doubling?
 	ContentHTML = Content
-	ContentHTML = ReplWithEsc(ContentHTML, '[staticoso:Site:AbsoluteRoot]', SiteRoot)
+	ContentHTML = DictReplWithEsc(
-	ContentHTML = ReplWithEsc(ContentHTML, '[staticoso:Site:RelativeRoot]', GetPathLevels(PagePath))
+		ContentHTML, {
+			'[staticoso:Site:AbsoluteRoot]': SiteRoot,
+			'[staticoso:Site:RelativeRoot]': GetPathLevels(PagePath)
+		})
 	for e in Meta['Macros']:
 		ContentHTML = ReplWithEsc(ContentHTML, f"[:{e}:]", Meta['Macros'][e])
 	for e in FolderRoots:
 		ContentHTML = ReplWithEsc(ContentHTML, f"[staticoso:Folder:{e}:AbsoluteRoot]", FolderRoots[e])
 	for e in Categories:
 		ContentHTML = ReplWithEsc(ContentHTML, f"<span>[staticoso:Category:{e}]</span>", Categories[e])
+		ContentHTML = ReplWithEsc(ContentHTML, f"[staticoso:Category:{e}]", Categories[e])
 	SlimHTML = HTMLPagesList + ContentHTML
 
 	return HTML, ContentHTML, SlimHTML, Description, Image
 
-def DoMinifyHTML(HTML):
+def MakeSite(OutputDir, LimitFiles, TemplatesText, StaticPartsText, DynamicParts, DynamicPartsText, ConfMenu, GlobalMacros, SiteName, BlogName, SiteTagline, SiteTemplate, SiteDomain, SiteRoot, FolderRoots, SiteLang, Locale, Minify, MinifyKeepComments, NoScripts, ImgAltToTitle, ImgTitleToAlt, Sorting, MarkdownExts, AutoCategories):
-	return htmlmin.minify(
-		input=HTML,
-		remove_comments=True,
-		remove_empty_space=True,
-		remove_all_empty_space=False,
-		reduce_empty_attributes=True,
-		reduce_boolean_attributes=True,
-		remove_optional_attribute_quotes=True,
-		convert_charrefs=True,
-		keep_pre=True)
-
-def MakeSite(OutputDir, LimitFiles, TemplatesText, StaticPartsText, DynamicParts, DynamicPartsText, ConfMenu, GlobalMacros, SiteName, BlogName, SiteTagline, SiteTemplate, SiteDomain, SiteRoot, FolderRoots, SiteLang, Locale, Minify, NoScripts, ImgAltToTitle, ImgTitleToAlt, Sorting, MarkdownExts, AutoCategories):
 	PagesPaths, PostsPaths, Pages, MadePages, Categories = [], [], [], [], {}
 	for Ext in FileExtensions['Pages']:
 		for File in Path('Pages').rglob(f"*.{Ext}"):
@@ -435,15 +439,7 @@ def MakeSite(OutputDir, LimitFiles, TemplatesText, StaticPartsText, DynamicParts
 			if not Exists:
 				File = f"Categories/{Cat}.md"
 				FilePath = f"{OutputDir}/{File}"
-				WriteFile(FilePath, f"""\
+				WriteFile(FilePath, CategoryPageTemplate.format(Title=Cat))
-// Title: {Cat}
-// Type: Page
-// Index: True
-
-# {Cat}
-
-<div><span>[staticoso:Category:{Cat}]</span></div>
-""")
 				Content, Titles, Meta = PagePreprocessor(FilePath, SiteRoot)
 				Pages += [[File, Content, Titles, Meta]]
 
@@ -497,7 +493,7 @@ def MakeSite(OutputDir, LimitFiles, TemplatesText, StaticPartsText, DynamicParts
 			Locale=Locale)
 
 		if Minify:
-			HTML = DoMinifyHTML(HTML)
+			HTML = DoMinifyHTML(HTML, MinifyKeepComments)
 		if NoScripts:
 			HTML = StripTags(HTML, ['script'])
 		if ImgAltToTitle or ImgTitleToAlt:

Source/Modules/Utils.py

@@ -84,6 +84,7 @@ def FindAllIndex(Str, Sub):
 		yield i
 		i = Str.find(Sub, i+1)
 
+# Replace substrings in a string, except when an escape char is prepended
 def ReplWithEsc(Str, Find, Repl, Esc='\\'):
 	New = ''
 	Sects = Str.split(Find)
@@ -101,6 +102,11 @@ def ReplWithEsc(Str, Find, Repl, Esc='\\'):
 				New += Repl + e
 	return New
 
+def DictReplWithEsc(Str, Dict, Esc='\\'):
+	for Item in Dict:
+		Str = ReplWithEsc(Str, Item, Dict[Item], Esc='\\')
+	return Str
+
 def NumsFromFileName(Path):
 	Name = Path.split('/')[-1]
 	Split = len(Name)