Transition to monorepo on a new Dev branch

This commit is contained in:
2023-02-22 10:29:46 +01:00
parent 8436f03ec7
commit 3a483dc0ef
3712 changed files with 751 additions and 11 deletions

View File

@@ -0,0 +1,98 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
import time
from Libs.dateutil.parser import parse as date_parse
from Libs.mastodon import Mastodon
from Modules.HTML import *
from Modules.Utils import *
def MastodonGetSession(InstanceURL, Token):
return Mastodon(
api_base_url=InstanceURL,
access_token=Token)
def MastodonGetMyID(Session):
return Session.me()['id']
def MastodonGetPostsFromUserID(Session, UserID):
return Session.account_statuses(
UserID,
exclude_replies=True)
def MastodonDoPost(Session, Text, Lang=None, Visibility='public'):
if Text:
return Session.status_post(
Text,
language=Lang,
visibility=Visibility)
def MastodonGetLinkFromPost(Post, Domain=None):
Parse = MkSoup(Post['content'])
if Parse.a:
Link = Parse.find_all('a')[-1]['href']
if not Domain or (Domain and Link.startswith(Domain)):
return {
'Post': Post['uri'],
'Link': Link}
return None
def MastodonGetAllLinkPosts(Session, Domain=None):
Posts = []
for p in MastodonGetPostsFromUserID(Session, MastodonGetMyID(Session)):
Post = MastodonGetLinkFromPost(p, Domain)
if Post:
Posts += [Post]
return Posts
def MastodonShare(Flags, Pages, Locale):
SaidPosting = False
SiteDomain, SiteLang = Flags['SiteDomain'], Flags['SiteLang']
InstanceURL, Token = Flags['MastodonURL'], Flags['MastodonToken']
TypeFilter, HoursLimit, CategoryFilter = Flags['ActivityPubTypeFilter'], Flags['ActivityPubHoursLimit'], Flags['FeedCategoryFilter']
Session = MastodonGetSession(InstanceURL, Token)
Posts = MastodonGetAllLinkPosts(Session, SiteDomain)
Pages.sort()
for File, Content, Titles, Meta, ContentHTML, SlimHTML, Description, Image in Pages:
if (not TypeFilter or (TypeFilter and (Meta['Type'] == TypeFilter or TypeFilter == '*'))) and (not CategoryFilter or (CategoryFilter and (CategoryFilter in Meta['Categories'] or CategoryFilter == '*'))):
URL = f"{SiteDomain}/{StripExt(File)}.html"
DoPost = True
for p in Posts:
if p['Link'] in [URL]+Meta['URLs']:
DoPost = False
break
if DoPost and Meta['Feed'] == 'True' and (not HoursLimit or (Meta['CreatedOn'] and time.time() - time.mktime(date_parse(Meta['CreatedOn']).timetuple()) < 60*60*HoursLimit)):
Desc = ''
Paragraphs = MkSoup(ContentHTML).p.get_text().split('\n')
Read = '...' + Locale['ReadFullPost'] + ':\n'
for p in Paragraphs:
if p and len(Read+Desc+p)+25 < 500:
Desc += p + '\n\n'
else:
if Desc:
break
else:
Desc = p[:500-25-5-len(Read)] + '...'
if not SaidPosting:
print("[I] Posting to Mastodon")
SaidPosting = True
time.sleep(5) # Prevent flooding
Post = MastodonGetLinkFromPost(
Post=MastodonDoPost(
Session,
Text=Desc+Read+URL,
Lang=SiteLang),
Domain=SiteDomain)
if Post:
Posts += [Post]
return Posts

View File

@@ -0,0 +1,77 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
import configparser
from ast import literal_eval
DefConf = {
"Logging": 20,
"Threads": 0,
"DiffBuild": False,
"OutDir": "public",
"SiteLang": "en",
"SiteTemplate": "Default.html",
"ActivityPubTypeFilter": "Post",
"ActivityPubHoursLimit": 168,
"CategoriesUncategorized": "Uncategorized",
"FeedCategoryFilter": "Blog",
"FeedEntries": 10,
"JournalRedirect": False
}
def LoadConfFile(File):
Conf = configparser.ConfigParser()
Conf.optionxform = str
Conf.read(File)
return Conf
def LoadConfStr(Str):
Conf = configparser.ConfigParser()
Conf.optionxform = str
Conf.read_string(Str)
return Conf
def ReadConf(Conf, Sect, Opt=None):
if Opt:
if Conf.has_option(Sect, Opt):
return Conf[Sect][Opt]
else:
if Conf.has_section(Sect):
return Conf[Sect]
return None
def EvalOpt(Opt):
if Opt:
return literal_eval(Opt)
else:
return None
# TODO: Cleaning
def OptionChoose(Default, Primary, Secondary, Tertiary=None):
return Primary if Primary != None else Secondary if Secondary != None else Tertiary if Tertiary != None else Default
def OptChoose(Default, Primary, Secondary, Tertiary=None):
return OptionChoose(Default, Primary, Secondary, Tertiary=None)
def DefConfOptChoose(Key, Primary, Secondary):
return OptChoose(DefConf[Key], Primary, Secondary)
def StringBoolChoose(Default, Primary, Secondary):
Var = Default
Check = Primary if Primary != None else Secondary
if type(Check) == bool:
Var = Check
elif type(Check) == str:
if Check in ('True', 'All', '*'):
Var = True
elif Check in ('False', 'None'):
Var = False
return Var
def StrBoolChoose(Default, Primary, Secondary):
return StringBoolChoose(Default, Primary, Secondary)

View File

@@ -0,0 +1,221 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
from base64 import b64encode
from Modules.Globals import *
from Modules.HTML import *
from Modules.Utils import *
JournalHeadings = ('h2','h3','h4','h5')
JournalTitleDecorators = {'(':')', '[':']', '{':'}'}
#JournalStyles = {
# "Default": {},
# "details": {}
#}
HTMLSectionTitleLine = '<h{Index} class="SectionHeading staticoso-SectionHeading"><span class="SectionLink staticoso-SectionLink"><a href="#{DashTitle}"><span>»</span></a> </span><span class="SectionTitle staticoso-SectionTitle" id="{DashTitle}">{Title}</span></h{Index}>'
PugSectionTitleLine = "{Start}{Heading}.SectionHeading.staticoso-SectionHeading #[span.SectionLink.staticoso-SectionLink #[a(href='#{DashTitle}') #[span »]] ]#[span#{DashTitle}.SectionTitle.staticoso-SectionTitle {Rest}]"
CategoryPageTemplate = """\
// Title: {Name}
// Type: Page
// Index: True
# {Name}
<div><staticoso:Category:{Name}></div>
"""
RedirectPageTemplate = """\
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8"/>
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
<title>{TitlePrefix}Redirect</title>
<link rel="canonical" href="{SiteDomain}/{DestURL}"/>
<meta http-equiv="refresh" content="0; url='{DestURL}'"/>
</head>
<body>
<p><a href="{DestURL}">{StrClick}</a> {StrRedirect}.</p>
</body>
</html>
"""
HTMLCommentsBlock = '<br><h3>{StrComments}</h3><a href="{URL}" rel="noopener" target="_blank">{StrOpen} <span class="twa twa-↗️"><span>↗️</span></span></a>'
def DashifyTitle(Title:str, Done:list=[]):
return UndupeStr(DashifyStr(Title.lstrip(' ').rstrip(' ')), Done, '-')
# Generate HTML tree list (nested list) from our internal metaformat, such as:
# :Item 1 \\ <li>Item 1<ul>
# .:Item 2 ============\\ <li>Item 2<ul>
# ..:Item 3 ============// <li>Item 3</li></ul></li></ul></li>
# :Item 4 // <li>Item 4</li>
def GenHTMLTreeList(MetaList:str, Type:str='ul', Class:str=""):
HTML = ''
Lines = MetaList.splitlines()
CurDepth, NextDepth, PrevDepth = 0, 0, 0
for i,e in enumerate(Lines):
CurDepth = e.find(':')
NextDepth = Lines[i+1].find(':') if i+1 < len(Lines) else 0
HTML += '\n<li>' + e[CurDepth+1:]
if NextDepth == CurDepth:
HTML += '</li>'
elif NextDepth > CurDepth:
HTML += f'\n<{Type}>' * (NextDepth - CurDepth)
elif NextDepth < CurDepth:
HTML += f'</li>\n</{Type}>' * (CurDepth - NextDepth) + '</li>'
PrevDepth = CurDepth
return f'<{Type} class="staticoso-TreeList {Class}">{HTML}\n</{Type}>'
def MakeLinkableTitle(Line:str, Title:str, DashTitle:str, Type:str):
if Type == 'md':
Index = Title.split(' ')[0].count('#')
return HTMLSectionTitleLine.format(
Index=Index,
DashTitle=DashTitle,
Title=Title[Index+1:])
elif Type == 'pug':
Index = Line.find('h')
return PugSectionTitleLine.format(
Start=Line[:Index],
Heading=Line[Index:Index+2],
Rest=Line[Index+2:],
DashTitle=DashTitle)
def GetTitle(FileName:str, Meta:dict, Titles:list, Prefer:str='MetaTitle', BlogName:str=None):
if Prefer == 'BodyTitle':
Title = Titles[0].lstrip('#') if Titles else Meta['Title'] if Meta['Title'] else FileName
elif Prefer == 'MetaTitle':
Title = Meta['Title'] if Meta['Title'] else Titles[0].lstrip('#') if Titles else FileName
elif Prefer == 'HTMLTitle':
Title = Meta['HTMLTitle'] if Meta['HTMLTitle'] else Meta['Title'] if Meta['Title'] else Titles[0].lstrip('#') if Titles else FileName
if Meta['Type'] == 'Post' and BlogName and 'Blog' in Meta['Categories']:
Title += ' - ' + BlogName
return Title
def GetDescription(Meta:dict, BodyDescription:str, Prefer:str='MetaDescription'):
if Prefer == 'BodyDescription':
Description = BodyDescription if BodyDescription else Meta['Description'] if Meta['Description'] else ''
elif Prefer == 'MetaDescription':
Description = Meta['Description'] if Meta['Description'] else BodyDescription if BodyDescription else ''
return Description
def GetImage(Meta:dict, BodyImage:str, Prefer:str='MetaImage'):
if Prefer == 'BodyImage':
Image = BodyImage if BodyImage else Meta['Image'] if Meta['Image'] else ''
elif Prefer == 'MetaImage':
Image = Meta['Image'] if Meta['Image'] else BodyImage if BodyImage else ''
return Image
def MakeContentHeader(Meta:dict, Locale:dict, Categories:str=''):
Header = ''
for e in ['CreatedOn', 'EditedOn']:
if Meta[e]:
Header += f'<span class="staticoso-ContentHeader-{e}" id="staticoso-ContentHeader-{e}"><span class="staticoso-Label">{Locale[e]}</span>: <span class="staticoso-Value">{Meta[e]}</span></span><br>'
if Categories:
Header += f'<span class="staticoso-ContentHeader-Categories" id="staticoso-ContentHeader-Categories"><span class="staticoso-Label">{Locale["Categories"]}</span>:<span class="staticoso-Value">{Categories.removesuffix(" ")}</span></span><br>'
if Meta['Index'].lower() in PageIndexStrNeg:
Header += f'<span class="staticoso-ContentHeader-Index" id="staticoso-ContentHeader-Index"><span class="staticoso-Value">{Locale["Unlisted"]}</span></span><br>'
return f'<p>{Header}</p>'
def MakeCategoryLine(File:str, Meta:dict):
Categories = ''
for Cat in Meta['Categories']:
Categories += f' <a href="{GetPathLevels(File)}Categories/{Cat}.html">{html.escape(Cat)}</a> '
return Categories
def MakeListTitle(File:str, Meta:dict, Titles:list, Prefer:str, BlogName:str, PathPrefix:str=''):
Title = GetTitle(File.split('/')[-1], Meta, Titles, Prefer, BlogName).lstrip().rstrip()
Link = False if Meta['Index'] == 'Unlinked' else True
if Link:
Href = f'{PathPrefix}{StripExt(File)}.html'
Title = f'<a href="{Href}">{Title}</a>'
#else:
# Title = f'<span class="staticoso-ListItem-Plain">{Title}</span>'
if Meta['Type'] == 'Post':
CreatedOn = Meta['CreatedOn'] if Meta['CreatedOn'] else '?'
Title = f"<span>[<time>{CreatedOn}</time>]</span> {Title}"
return Title
def FormatTitles(Titles:list, Flatten=False):
# TODO: Somehow titles written in Pug can end up here and don't work, they should be handled
List, DashyTitles = '', []
for t in Titles:
n = 0 if Flatten else t.split(' ')[0].count('#')
Level = '.' * (n-1) + ':'
Title = MkSoup(t.lstrip('#')).get_text()
DashyTitle = DashifyTitle(Title, DashyTitles)
DashyTitles += [DashyTitle]
List += f'{Level}<a href="#{DashyTitle}">{html.escape(Title)}</a>\n'
return GenHTMLTreeList(List)
# Clean up a generic HTML tree such that it's compliant with the HTML Journal standard
# (https://m15o.ichi.city/site/subscribing-to-a-journal-page.html);
# basis is: find an element with the JournalBody attr., and group its direct children as <article>s
def MakeHTMLJournal(Flags, Locale, FilePath, HTML):
Soup, Journal, Entries = MkSoup(HTML), '', []
for t in Soup.find_all(attrs={"htmljournal":True}):
#JournalStyle = JournalStyles[t.attrs["journalstyle"]] if 'journalstyle' in t.attrs and t.attrs["journalstyle"] in JournalStyles else JournalStyles['Default']
for c in t.children: # Entries, some might be entirely grouped in their own element but others could not, use headings as separators
for ct in MkSoup(str(c)).find_all():
# Transform (almost, for now I reserve some) any heading into h2 and remove any attributes
if ct.name in JournalHeadings:
Title = ct.text.strip().removeprefix('»').strip()
Chr0 = Title[0]
# Remove leading symbols before date
if Chr0 in JournalTitleDecorators.keys():
Idx = Title.find(JournalTitleDecorators[Chr0])
Title = Title[1:Idx] + ' - ' + Title[Idx+2:]
if Journal:
Journal += '\n</article><br>\n'
Journal += f'\n<article>\n<h2>{Title}</h2>\n'
elif ct.name == 'p': # We should handle any type to preserve <details> and things
Journal += str(ct)
FileName = FilePath.split('/')[-1]
URL = f'{Flags["SiteDomain"]}/{StripExt(FilePath)}.Journal.html'
Redirect = f"""<meta http-equiv="refresh" content="0; url='./{FileName}'">""" if Flags["JournalRedirect"] else ''
# Instead of copying stuff from the full page, for now we use dedicated title, header, footer, and pagination
Title = t.attrs["journaltitle"] if 'journaltitle' in t.attrs else f'"{StripExt(FileName)}" Journal - {Flags["SiteName"]}' if Flags["SiteName"] else f'"{StripExt(FileName)}" Journal'
FeedLink = f"""<a title="Journal Atom Feed" href="https://journal.miso.town/atom?url={URL}" target="_blank" rel="noopener"><img width="88" height="31" alt="Journal Atom Feed" title="Journal Atom Feed" src="data:image/png;base64,{b64encode(ReadFile(staticosoBaseDir()+'Assets/Feed-88x31.png', 'rb')).decode()}"></a>""" if Flags["SiteDomain"] else ''
Header = t.attrs["journalheader"] if 'journalheader' in t.attrs else f"""\
<p>
<i>{Locale["StrippedDownNotice"].format(Link="./"+FileName)}</i>
<a title="Valid HTML Journal" href="https://journal.miso.town" target="_blank" rel="noopener"><img alt="Valid HTML Journal" title="Valid HTML Journal" width="88" height="31" src="data:image/png;base64,{b64encode(ReadFile(staticosoBaseDir()+'Assets/Valid-HTML-Journal-88x31.png', 'rb')).decode()}"></a>
{FeedLink}
</p>
"""
Journal = f"""\
<!--
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8"/>
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
<title>{Title}</title>
<link rel="canonical" href="{URL}"/>
{Redirect}
</head>
<body>
--->
<h1>{Title}</h1>
<header id="Header">
{Header}
<div id="staticoso-LinkToFooter"><b>[<big><a href="#Footer"><span class="twa twa-⬇️"><span>⬇️</span></span> Footer</a></big>]</b></div>
</header><br>
{Journal}
</article><br>
<footer id="Footer">
<div id="staticoso-LinkToHeader"><b>[<big><a href="#Header"><span class="twa twa-⬆️"><span>⬆️</span></span> Header</a></big>]</b></div>
{t.attrs["journalfooter"] if "journalfooter" in t.attrs else ""}
</footer>
<!--
</body>
</html>
--->
"""
return Journal

View File

@@ -0,0 +1,61 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
# TODO: Either switch feed generation lib, or rewrite the 'lxml' module, so that no modules have to be compiled and the program is 100% portable
from Libs.feedgen.feed import FeedGenerator
from Modules.Utils import *
def MakeFeed(Flags, Pages, FullSite=False):
CategoryFilter = Flags['FeedCategoryFilter']
MaxEntries = Flags['FeedEntries']
Feed = FeedGenerator()
Link = Flags['SiteDomain'] if Flags['SiteDomain'] else ' '
Feed.id(Link)
Feed.title(Flags['SiteName'] if Flags['SiteName'] else 'Untitled Site')
Feed.link(href=Link, rel='alternate')
Feed.description(Flags['SiteTagline'] if Flags['SiteTagline'] else ' ')
if Flags['SiteDomain']:
Feed.logo(Flags['SiteDomain'] + '/favicon.png')
Feed.language(Flags['SiteLang'])
DoPages = []
for e in Pages:
if FullSite or (not FullSite and MaxEntries != 0 and e[3]['Type'] == 'Post' and e[3]['Feed'] == 'True'): # No entry limit if site feed
DoPages += [e]
MaxEntries -= 1
DoPages.reverse()
for File, Content, Titles, Meta, ContentHTML, SlimHTML, Description, Image in DoPages:
if FullSite or (not FullSite and Meta['Type'] == 'Post' and (not CategoryFilter or (CategoryFilter and (CategoryFilter in Meta['Categories'] or CategoryFilter == '*')))):
Entry = Feed.add_entry()
FileName = File.split('/')[-1]
File = f"{StripExt(File)}.html"
Content = ReadFile(f"{Flags['OutDir']}/{File}")
Link = Flags['SiteDomain'] + '/' + File if Flags['SiteDomain'] else ' '
CreatedOn = GetFullDate(Meta['CreatedOn'])
EditedOn = GetFullDate(Meta['EditedOn'])
Entry.id(Link)
Title = Meta['Title'] if Meta['Title'] else Titles[0].lstrip('#') if Titles else FileName
Entry.title(Title.lstrip().rstrip())
Entry.description(Description)
Entry.link(href=Link, rel='alternate')
if not FullSite: # Avoid making an enormous site feed file...
Entry.content(ContentHTML, type='html')
if CreatedOn:
Entry.pubDate(CreatedOn)
EditedOn = EditedOn if EditedOn else CreatedOn if CreatedOn and not EditedOn else '1970-01-01T00:00+00:00'
Entry.updated(EditedOn)
if not os.path.exists(f"{Flags['OutDir']}/feed"):
os.mkdir(f"{Flags['OutDir']}/feed")
FeedType = 'site.' if FullSite else ''
Feed.atom_file(f"{Flags['OutDir']}/feed/{FeedType}atom.xml", pretty=(not Flags['MinifyOutput']))
Feed.rss_file(f"{Flags['OutDir']}/feed/{FeedType}rss.xml", pretty=(not Flags['MinifyOutput']))

View File

@@ -0,0 +1,59 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
# TODO: Write the Python HTML2Gemtext converter
from Libs.bs4 import BeautifulSoup
from Modules.HTML import *
from Modules.Utils import *
def FixGemlogDateLine(Line):
if len(Line) >= 2 and Line[0] == '[' and Line[1].isdigit():
Line = Line[1:]
else:
Words = Line.split(' ')
if len(Words) >= 2 and len(Words[1]) >= 2 and Words[1][0] == '[' and Words[1][1].isdigit():
Line = Words[0] + '\n' + Words[1][1:] + ' ' + ' '.join(Words[2:])
return Line
def GemtextCompileList(Flags, Pages, LimitFiles):
Cmd = ''
for File, Content, Titles, Meta, ContentHTML, SlimHTML, Description, Image in Pages:
if IsLightRun(File, LimitFiles):
continue
Src = f"{Flags['OutDir']}.gmi/{StripExt(File)}.html.tmp"
Dst = f"{Flags['OutDir']}.gmi/{StripExt(File)}.gmi"
SlimHTML = StripAttrs(SlimHTML)
for i in ('ol', 'ul', 'li'):
for j in ('<'+i+'>', '</'+i+'>'):
SlimHTML = SlimHTML.replace(j, '')
WriteFile(Src, SlimHTML.replace('</a>', '</a><br>').replace('.html', '.gmi')) # TODO: Adjust links properly..
Cmd += f'cat "{Src}" | html2gmi > "{Dst}"; '
if Cmd:
os.system(Cmd)
for File, Content, Titles, Meta, ContentHTML, SlimHTML, Description, Image in Pages:
if IsLightRun(File, LimitFiles):
continue
Dst = f"{Flags['OutDir']}.gmi/{StripExt(File)}.gmi"
Gemtext = ''
for Line in ReadFile(Dst).splitlines():
Line = FixGemlogDateLine(Line)
Gemtext += Line + '\n'
WriteFile(Dst, Flags['GemtextHeader'] + Gemtext)
def FindEarliest(Str, Items):
Pos, Item = 0, ''
for Item in Items:
Str.find(Item)
return Pos, Item
def ParseTag(Content):
print(Content)
Parse = BeautifulSoup(str(Content), 'html.parser')
Tag = Parse.find()

View File

@@ -0,0 +1,23 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
ReservedPaths = ('Site.ini', 'Assets', 'Pages', 'Posts', 'Templates', 'StaticParts', 'DynamicParts')
FileExtensions = {
'Pages': ('htm', 'html', 'markdown', 'md', 'pug', 'txt'),
'HTML': ('.htm', '.html'),
'Markdown': ('.markdown', '.md'),
'Tmp': ('htm', 'markdown', 'md', 'pug', 'txt')}
PosStrBools = ('true', 'yes', 'on', '1', 'enabled')
NegStrBools = ('false', 'no', 'off', '0', 'disabled')
PageIndexStrPos = tuple(list(PosStrBools) + ['all', 'listed', 'indexed', 'unlinked'])
PageIndexStrNeg = tuple(list(NegStrBools) + ['none', 'unlisted', 'unindexed', 'hidden'])
InternalMacrosWraps = [['[', ']'], ['<', '>']]

100
App/Source/Modules/HTML.py Normal file
View File

@@ -0,0 +1,100 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
import html
import warnings
from Libs import htmlmin
from Libs.bs4 import BeautifulSoup
from Modules.Utils import *
# Suppress useless bs4 warnings
warnings.filterwarnings('ignore', message='The input looks more like a filename than markup.')
def MkSoup(HTML):
return BeautifulSoup(HTML, 'html.parser')
def StripAttrs(HTML):
Soup = MkSoup(HTML)
Tags = Soup.find_all()
for t in Tags:
if 'href' not in t.attrs and 'src' not in t.attrs:
t.attrs = {}
return str(Soup)
def StripTags(HTML, ToStrip): # Remove desired tags from the HTML
Soup = MkSoup(HTML)
Tags = Soup.find_all()
for t in Tags:
if t.name in ToStrip:
t.replace_with('')
return str(Soup)
def DoHTMLFixPre(HTML):
if not ("<pre>" in HTML or "<pre " in HTML):
return HTML
Soup = MkSoup(HTML)
Tags = Soup.find_all('pre')
for t in Tags:
FirstLine = str(t).splitlines()[0].lstrip().rstrip()
if FirstLine.endswith('>'):
New = MkSoup(str(t).replace('\n', '', 1))
t.replace_with(New.pre)
return str(Soup)
def WriteImgAltAndTitle(HTML, AltToTitle, TitleToAlt): # Adds alt or title attr. to <img> which only have one of them
Soup = MkSoup(HTML)
Tags = Soup.find_all('img')
for t in Tags:
if AltToTitle and 'alt' in t.attrs and 'title' not in t.attrs:
t.attrs.update({'title': t.attrs['alt']})
elif TitleToAlt and 'title' in t.attrs and 'alt' not in t.attrs:
t.attrs.update({'alt': t.attrs['title']})
return str(Soup)
def AddToTagStartEnd(HTML, MatchStart, MatchEnd, AddStart, AddEnd): # This doesn't handle nested tags
StartPos, DidStart, DidEnd = None, 0, 0
for i,e in enumerate(HTML):
FilterStart = HTML[i:i+len(MatchStart)]
FilterEnd = HTML[i:i+len(MatchEnd)]
if DidStart == 0 and FilterStart == MatchStart:
StartPos = i
if AddStart:
HTML = HTML[:i] + AddStart + HTML[i:]
DidStart = 2
if DidEnd == 0 and FilterEnd == MatchEnd and StartPos and i > StartPos:
StartPos = None
if AddEnd:
HTML = HTML[:i+len(MatchEnd)] + AddEnd + HTML[i+len(MatchEnd):]
DidEnd = 2
if DidStart > 0:
DidStart -= 1
if DidEnd > 0:
DidEnd -= 1
return HTML
def SquareFnrefs(HTML): # Different combinations of formatting for Soup .prettify, .encode, .decode break different page elements, don't use this for now
Soup = MkSoup(HTML)
Tags = Soup.find_all('sup')
for t in Tags:
if 'id' in t.attrs and t.attrs['id'].startswith('fnref:'):
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)

View File

@@ -0,0 +1,36 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
import logging
import sys
from Modules.Config import *
LoggingFormat = '[%(levelname)s] %(message)s'
LoggingLevels = {
"Debug": {"Name":"D", "Num":15},
"Info": {"Name":"I", "Num":20},
"Warning": {"Name":"W", "Num":30},
"Error": {"Name":"E", "Num":40}}
def SetupLogging(Level):
logging.basicConfig(format=LoggingFormat, stream=sys.stdout, level=Level)
logging.addLevelName(15, 'D') # Standard (10) Debug level makes third-party modules spam
logging.addLevelName(20, 'I')
logging.addLevelName(30, 'W')
logging.addLevelName(40, 'E')
def ConfigLogging(Level):
Num = DefConf['Logging']
if type(Level) == str:
if Level.isdecimal():
Num = int(Level)
else:
if Level.lower() in LoggingLevels:
Num = LoggingLevels['Level']['Num']
SetupLogging(Num)

View File

@@ -0,0 +1,20 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
from Libs.markdown import markdown
MarkdownExtsDefault = ('attr_list', 'def_list', 'fenced_code', 'footnotes', 'md_in_html', 'tables')
def MarkdownHTMLEscape(Str, Extensions=()): # WIP
Text = ''
for i,e in enumerate(Str):
if ('mdx_subscript' or 'markdown_del_ins') in Extensions and e == '~':
e = '&#x7E;'
Text += e
return Text

24
App/Source/Modules/Pug.py Normal file
View File

@@ -0,0 +1,24 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
# TODO: Write a native Pug parser; There is one already available for Python but seems broken / out-of-date
import os
from Modules.Utils import *
def PugCompileList(OutputDir, Pages, LimitFiles):
# Pug-cli seems to shit itself with folder paths as input, so we pass ALL the files as arguments
Paths = ''
for File, Content, Titles, Meta in Pages:
if File.lower().endswith('.pug') and (LimitFiles == False or File in LimitFiles):
Path = f'{OutputDir}/{File}'
WriteFile(Path, Content)
Paths += f'"{Path}" '
if Paths:
os.system(f'pug -P {Paths} > /dev/null')

707
App/Source/Modules/Site.py Normal file
View File

@@ -0,0 +1,707 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
import shutil
from datetime import datetime
from multiprocessing import Pool, cpu_count
from Libs.bs4 import BeautifulSoup
from Modules.Config import *
from Modules.Elements import *
from Modules.Globals import *
from Modules.HTML import *
from Modules.Logging import *
from Modules.Markdown import *
from Modules.Pug import *
from Modules.Utils import *
# Menu styles:
# - Simple: Default, Flat, Line
# - Others: Excerpt, Image, Preview (Excerpt + Image), Full
def GetHTMLPagesList(Pages, BlogName, SiteRoot, PathPrefix, CallbackFile=None, Unite=[], Type=None, Limit=None, PathFilter='', Category=None, For='Menu', MarkdownExts=(), MenuStyle='Default', ShowPaths=True):
Flatten, SingleLine, DoneCount, PrevDepth = False, False, 0, 0
if MenuStyle == 'Flat':
Flatten = True
elif MenuStyle == 'Line':
ShowPaths, SingleLine = False, True
List, ToPop, LastParent = '', [], []
IndexPages = Pages.copy()
for e in IndexPages:
if e[3]['Index'].lower() in PageIndexStrNeg:
IndexPages.remove(e)
for i,e in enumerate(IndexPages):
if Type and e[3]['Type'] != Type:
ToPop += [i]
ToPop = RevSort(ToPop)
for i in ToPop:
IndexPages.pop(i)
if Type == 'Page':
IndexPages = OrderPages(IndexPages)
for i,e in enumerate(Unite):
if e:
IndexPages.insert(i, [e, None, None, {'Type':Type, 'Index':'True', 'Order':'Unite'}])
for File, Content, Titles, Meta in IndexPages:
# Allow for the virtual "Pages/" prefix to be used in path filtering
TmpPathFilter = PathFilter
if TmpPathFilter.startswith('Pages/'):
TmpPathFilter = TmpPathFilter[len('Pages/'):]
if File.startswith('Posts/'):
continue
if (not Type or (Meta['Type'] == Type and CanIndex(Meta['Index'], For))) and (not Category or Category in Meta['Categories']) and File.startswith(TmpPathFilter) and File != CallbackFile and (not Limit or Limit > DoneCount):
Depth = (File.count('/') + 1) if Meta['Order'] != 'Unite' else 1
# Folder names are handled here
if Depth > 1 and Meta['Order'] != 'Unite':
CurParent = File.split('/')[:-1]
for i,s in enumerate(CurParent):
if LastParent != CurParent and ShowPaths:
LastParent = CurParent
Levels = '.' * ((Depth-2+i) if not Flatten else 0) + ':'
# If search node endswith index, it's a page; else, it's a folder
if StripExt(File).endswith('index'):
Title = MakeListTitle(File, Meta, Titles, 'HTMLTitle', BlogName, PathPrefix)
DoneCount += 1
else:
Title = CurParent[Depth-2+i]
if SingleLine:
List += f' <span>{Title}</span> '
else:
List += f'{Levels}<span>{Title}</span>\n'
# Pages with any other path
if not (Depth > 1 and StripExt(File).split('/')[-1] == 'index'):
Levels = '.' * ((Depth-1) if not Flatten else 0) + ':'
DoneCount += 1
if Meta['Order'] == 'Unite':
Title = markdown(MarkdownHTMLEscape(File, MarkdownExts), extensions=MarkdownExts).removeprefix('<p>').removesuffix('<p>')
else:
Title = MakeListTitle(File, Meta, Titles, 'HTMLTitle', BlogName, PathPrefix)
if SingleLine:
List += ' <span>' + Title + '</span> '
else:
List += Levels + Title + '\n'
if MenuStyle in ('Default', 'Flat'):
return GenHTMLTreeList(List, Class="staticoso-PagesList")
elif MenuStyle in ('Line', 'Excerpt', 'Image', 'Preview', 'Full'):
return List
def CheckHTMLCommentLine(Line):
if Line.startswith('<!--'):
Line = Line[4:].lstrip()
if Line.endswith('-->'):
return Line
return None
def TemplatePreprocessor(Text):
Meta, MetaDefault = '', {
'MenuStyle': 'Default'}
for l in Text.splitlines():
ll = l.lstrip().rstrip()
lll = CheckHTMLCommentLine(ll)
if lll:
if lll.startswith('%'):
Meta += lll[1:-3].lstrip().rstrip() + '\n'
Meta = dict(ReadConf(LoadConfStr('[Meta]\n' + Meta), 'Meta'))
for i in MetaDefault:
if not i in Meta:
Meta.update({i:MetaDefault[i]})
return Meta
def FindPreprocLine(Line, Meta, Macros):
Changed = False
Line = Line.lstrip().rstrip()
lll = CheckHTMLCommentLine(Line)
if Line.startswith('//') or lll: # Find preprocessor lines
lll = Line[2:].lstrip()
if lll.startswith('%'):
Meta += lll[1:].lstrip() + '\n'
Changed = True
elif lll.startswith('$'):
Macros += lll[1:].lstrip() + '\n'
Changed = True
#if ll.startswith('<!--') and not ll.endswith('-->'): # Find comment and code blocks
# IgnoreBlocksStart += [l]
return (Meta, Macros, Changed)
def PagePreprocessor(Path:str, TempPath:str, Type, SiteTemplate, SiteRoot, GlobalMacros, CategoryUncategorized, LightRun=False):
File = ReadFile(Path)
Path = Path.lower()
Content, Titles, DashyTitles, HTMLTitlesFound, Macros, Meta, MetaDefault = '', [], [], False, '', '', {
'Template': SiteTemplate,
'Head': '',
'Style': '',
'Type': Type,
'Index': 'Unspecified',
'Feed': 'True',
'Title': '',
'HTMLTitle': '',
'Description': '',
'Image': '',
'Macros': {},
'Categories': [],
'URLs': [],
'CreatedOn': '',
'UpdatedOn': '',
'EditedOn': '',
'Order': None,
'Language': None,
'Downsync': None}
# Find all positions of '<!--', '-->', add them in a list=[[pos0,pos1,line0,line1],...]
for l in File.splitlines():
ll = l.lstrip().rstrip()
Meta, Macros, Changed = FindPreprocLine(ll, Meta, Macros)
if not Changed: # Find headings
#if line in ignore block:
# continue
Headings = ('h1', 'h2', 'h3', 'h4', 'h5', 'h6')
#if Path.endswith(FileExtensions['HTML']):
# if ll[1:].startswith(Headings):
# if ll[3:].startswith((" class='NoTitle", ' class="NoTitle')):
# Content += l + '\n'
# elif ll.replace(' ', ' ').startswith('// %'):
# pass
# else:
# Title = '#'*int(ll[2]) + ' ' + ll[4:]
# DashTitle = DashifyTitle(Title.lstrip('#'), DashyTitles)
# DashyTitles += [DashTitle]
# Titles += [Title]
# Content += MakeLinkableTitle(l, Title, DashTitle, 'pug') + '\n'
# else:
# Content += l + '\n'
if Path.endswith(FileExtensions['HTML']) and not HTMLTitlesFound:
Soup = BeautifulSoup(File, 'html.parser')
Tags = Soup.find_all()
for t in Tags:
if t.name in Headings:
Title = '#'*int(t.name[1]) + ' ' + str(t.text)
DashTitle = DashifyTitle(Title.lstrip('#'), DashyTitles)
DashyTitles += [DashTitle]
Titles += [Title]
t.replace_with(MakeLinkableTitle(None, Title, DashTitle, 'md'))
HTMLTitlesFound = True
Content = ''
TmpContent = str(Soup.prettify(formatter=None))
for cl in TmpContent.splitlines():
_, _, IsMetaLine = FindPreprocLine(cl, Meta, Macros)
if not IsMetaLine:
#print(cl)
Content += cl + '\n'
break
elif Path.endswith(FileExtensions['Markdown']):
lsuffix = ''
if ll.startswith(('-', '+', '*')):
lsuffix += ll[0]
ll = ll[1:].lstrip()
if ll.startswith('#') or (ll.startswith('<') and ll[1:].startswith(Headings)):
if ll.startswith('#'):
Title = ll
elif ll.startswith('<'):
if ll[3:].startswith((" class='NoTitle", ' class="NoTitle')):
Content += l + '\n'
continue
else:
Title = '#'*int(ll[2]) + ' ' + ll[4:]
DashTitle = DashifyTitle(MkSoup(Title.lstrip('#')).get_text(), DashyTitles)
DashyTitles += [DashTitle]
Titles += [Title]
Title = MakeLinkableTitle(None, Title, DashTitle, 'md')
# I can't remember why I put this but it was needed
Title = Title.replace('> </', '> </').replace(' </', '</')
Content += lsuffix + Title + '\n'
else:
Content += l + '\n'
elif Path.endswith('.pug'):
if ll.startswith(Headings):
if ll[2:].startswith(("(class='NoTitle", '(class="NoTitle')):
Content += l + '\n'
else:
Title = '#'*int(ll[1]) + ll[3:]
DashTitle = DashifyTitle(Title.lstrip('#'), DashyTitles)
DashyTitles += [DashTitle]
Titles += [Title]
# TODO: We should handle headers that for any reason already have parenthesis
if ll[2:] == '(':
Content += l + '\n'
else:
Content += MakeLinkableTitle(l, Title, DashTitle, 'pug') + '\n'
else:
Content += l + '\n'
elif Path.endswith('.txt'):
Content += l + '\n'
Meta = dict(ReadConf(LoadConfStr('[Meta]\n' + Meta), 'Meta'))
for i in MetaDefault:
if i in Meta:
# TODO: Handle strings with spaces but wrapped in quotes
if i == 'Categories':
Categories = Meta['Categories'].split(' ')
Meta['Categories'] = []
for j in Categories:
Meta['Categories'] += [j]
elif i == 'URLs':
URLs = Meta['URLs'].split(' ')
Meta['URLs'] = []
for j in URLs:
Meta['URLs'] += [j]
else:
Meta.update({i:MetaDefault[i]})
if Meta['UpdatedOn']:
Meta['EditedOn'] = Meta['UpdatedOn']
if Meta['Index'].lower() in ('default', 'unspecified', 'categories'):
if not Meta['Categories']:
Meta['Categories'] = [CategoryUncategorized]
if Meta['Type'].lower() == 'page':
Meta['Index'] = 'Categories'
elif Meta['Type'].lower() == 'post':
Meta['Index'] = 'True'
if GlobalMacros:
Meta['Macros'].update(GlobalMacros)
Meta['Macros'].update(ReadConf(LoadConfStr('[Macros]\n' + Macros), 'Macros'))
return [TempPath, Content, Titles, Meta]
def PagePostprocessor(FileType, Text:str, Meta:dict):
for e in Meta['Macros']:
Text = ReplWithEsc(Text, f"[: {e} :]", f"[:{e}:]")
return Text
def OrderPages(Old:list):
New, NoOrder, Max = [], [], 0
for i,e in enumerate(Old):
Curr = e[3]['Order']
if Curr:
if int(Curr) > Max:
Max = int(Curr)
else:
NoOrder += [e]
New = [None] * (Max+1)
for i,e in enumerate(Old):
Curr = e[3]['Order']
if Curr:
New[int(Curr)] = e
while None in New:
New.remove(None)
return New + NoOrder
def CanIndex(Index:str, For:str):
if Index.lower() in PageIndexStrNeg:
return False
elif Index.lower() in PageIndexStrPos:
return True
else:
return True if Index == For else False
def PatchHTML(File, HTML, StaticPartsText, DynamicParts, DynamicPartsText, HTMLPagesList, PagePath, Content, Titles, Meta, SiteDomain, SiteRoot, SiteName, BlogName, FolderRoots, Categories, SiteLang, Locale, LightRun):
HTMLTitles = FormatTitles(Titles)
BodyDescription, BodyImage = '', ''
if not File.lower().endswith('.txt'):
Soup = MkSoup(Content)
if not BodyDescription:# and Soup.p:
#BodyDescription = Soup.p.get_text()[:150].replace('\n', ' ').replace('"', "'") + '...'
for t in Soup.find_all('p'):
if t.get_text():
BodyDescription = t.get_text()[:150].replace('\n', ' ').replace('"', "'") + '...'
break
if not BodyImage and Soup.img and Soup.img['src']:
BodyImage = Soup.img['src']
#Content = SquareFnrefs(Content)
if '<a class="footnote-ref" ' in Content:
Content = AddToTagStartEnd(Content, '<a class="footnote-ref" ', '</a>', '[', ']')
if any(_ in Content for _ in ('<!-- noprocess />', '<!--noprocess/>', '</ noprocess -->', '</ noprocess --->', '</noprocess-->', '</noprocess--->')):
Content = DictReplWithEsc(
Content, {
'<!--<%noprocess>': '',
'<noprocess%>-->': '',
'<noprocess%>--->': '',
'<!-- noprocess />': '',
'<!--noprocess/>': '',
'</ noprocess -->': '',
'</ noprocess --->': '',
'</noprocess-->': '',
'</noprocess--->': ''})
Title = GetTitle(File.split('/')[-1], Meta, Titles, 'MetaTitle', BlogName)
Description = GetDescription(Meta, BodyDescription, 'MetaDescription')
Image = GetImage(Meta, BodyImage, 'MetaImage')
ContentHeader = MakeContentHeader(Meta, Locale, MakeCategoryLine(File, Meta))
TimeNow = datetime.now().strftime('%Y-%m-%d %H:%M')
RelativeRoot = GetPathLevels(PagePath)
if 'staticoso:DynamicPart:' in HTML: # Reduce risk of unnecessary cycles
for Line in HTML.splitlines():
Line = Line.lstrip().rstrip()
if (Line.startswith('[staticoso:DynamicPart:') and Line.endswith(']')) or (Line.startswith('<staticoso:DynamicPart:') and Line.endswith('>')):
Path = Line[len('<staticoso:DynamicPart:'):-1]
Section = Path.split('/')[-1]
if Section in DynamicParts:
Part = DynamicParts[Section]
Text = ''
if type(Part) == list:
for e in Part:
Text += DynamicPartsText[f"{Path}/{e}"] + '\n'
elif type(Part) == str:
Text = DynamicPartsText[f"{Path}/{Part}"]
else:
Text = ''
HTML = ReplWithEsc(HTML, f"[staticoso:DynamicPart:{Path}]", Text)
HTML = ReplWithEsc(HTML, f"<staticoso:DynamicPart:{Path}>", Text)
for i in range(2):
for e in StaticPartsText:
HTML = ReplWithEsc(HTML, f"[staticoso:StaticPart:{e}]", StaticPartsText[e])
HTML = ReplWithEsc(HTML, f"<staticoso:StaticPart:{e}>", StaticPartsText[e])
if LightRun:
HTML = None
else:
HTML = WrapDictReplWithEsc(HTML, {
#'[staticoso:PageHead]': Meta['Head'],
#'<staticoso:PageHead>': Meta['Head'],
# #DEPRECATION #
'staticoso:Site:Menu': HTMLPagesList,
'staticoso:Page:Lang': Meta['Language'] if Meta['Language'] else SiteLang,
'staticoso:Page:Chapters': HTMLTitles,
'staticoso:Page:Title': Title,
'staticoso:Page:Description': Description,
'staticoso:Page:Image': Image,
'staticoso:Page:Path': PagePath,
'staticoso:Page:Style': Meta['Style'],
################
'staticoso:SiteMenu': HTMLPagesList,
'staticoso:PageLang': Meta['Language'] if Meta['Language'] else SiteLang,
'staticoso:PageLanguage': Meta['Language'] if Meta['Language'] else SiteLang,
'staticoso:PageSections': HTMLTitles,
'staticoso:PageTitle': Title,
'staticoso:PageDescription': Description,
'staticoso:PageImage': Image,
'staticoso:PagePath': PagePath,
'staticoso:PageHead': Meta['Head'],
'staticoso:PageStyle': Meta['Style'],
# NOTE: Content is injected in page only at this point! Keep in mind for other substitutions
# #DEPRECATION #
'staticoso:Page:Content': Content,
'staticoso:Page:ContentInfo': ContentHeader,
'staticoso:Site:Name': SiteName,
'staticoso:Site:AbsoluteRoot': SiteRoot,
'staticoso:Site:RelativeRoot': RelativeRoot,
################
'staticoso:PageContent': Content,
'staticoso:PageContentInfo': ContentHeader,
'staticoso:BuildTime': TimeNow,
'staticoso:SiteDomain': SiteDomain,
'staticoso:SiteName': SiteName,
'staticoso:SiteAbsoluteRoot': SiteRoot,
'staticoso:SiteRelativeRoot': RelativeRoot,
}, InternalMacrosWraps)
for e in Meta['Macros']:
HTML = ReplWithEsc(HTML, f"[:{e}:]", Meta['Macros'][e])
for e in FolderRoots:
HTML = WrapDictReplWithEsc(HTML, {
f'staticoso:CustomPath:{e}': FolderRoots[e],
f'staticoso:Folder:{e}:AbsoluteRoot': FolderRoots[e], #DEPRECATED
}, InternalMacrosWraps)
for e in Categories:
HTML = WrapDictReplWithEsc(HTML, {
f'staticoso:Category:{e}': Categories[e],
f'staticoso:CategoryList:{e}': Categories[e],
}, InternalMacrosWraps)
HTML = ReplWithEsc(HTML, f'<span>[staticoso:Category:{e}]</span>', Categories[e]) #DEPRECATED
# TODO: Clean this doubling?
ContentHTML = Content
ContentHTML = WrapDictReplWithEsc(ContentHTML, {
# #DEPRECATION #
'[staticoso:Page:Title]': Title,
'[staticoso:Page:Description]': Description,
'[staticoso:Site:Name]': SiteName,
'[staticoso:Site:AbsoluteRoot]': SiteRoot,
'[staticoso:Site:RelativeRoot]': RelativeRoot,
################
'<staticoso:PageTitle>': Title,
'<staticoso:PageDescription>': Description,
'<staticoso:SiteDomain>': SiteDomain,
'<staticoso:SiteName>': SiteName,
'<staticoso:SiteAbsoluteRoot>': SiteRoot,
'<staticoso:SiteRelativeRoot>': RelativeRoot,
}, InternalMacrosWraps)
for e in Meta['Macros']:
ContentHTML = ReplWithEsc(ContentHTML, f"[:{e}:]", Meta['Macros'][e])
for e in FolderRoots:
ContentHTML = WrapDictReplWithEsc(ContentHTML, {
f'staticoso:CustomPath:{e}': FolderRoots[e],
f'staticoso:Folder:{e}:AbsoluteRoot': FolderRoots[e], #DEPRECATED
}, InternalMacrosWraps)
for e in Categories:
ContentHTML = WrapDictReplWithEsc(ContentHTML, {
f'staticoso:Category:{e}': Categories[e],
f'staticoso:CategoryList:{e}': Categories[e],
}, InternalMacrosWraps)
ContentHTML = ReplWithEsc(ContentHTML, f'<span>[staticoso:Category:{e}]</span>', Categories[e]) #DEPRECATED
return HTML, ContentHTML, Description, Image
def HandlePage(Flags, Page, Pages, Categories, LimitFiles, Snippets, ConfMenu, Locale):
File, Content, Titles, Meta = Page
OutDir, MarkdownExts, Sorting, MinifyKeepComments = Flags['OutDir'], Flags['MarkdownExts'], Flags['Sorting'], Flags['MinifyKeepComments']
SiteName, BlogName, SiteTagline = Flags['SiteName'], Flags['BlogName'], Flags['SiteTagline']
SiteTemplate, SiteLang = Flags['SiteTemplate'], Flags['SiteLang']
SiteDomain, SiteRoot, FolderRoots = Flags['SiteDomain'], Flags['SiteRoot'], Flags['FolderRoots']
AutoCategories, CategoryUncategorized = Flags['CategoriesAutomatic'], Flags['CategoriesUncategorized']
ImgAltToTitle, ImgTitleToAlt = Flags['ImgAltToTitle'], Flags['ImgTitleToAlt']
DynamicParts, DynamicPartsText, StaticPartsText, TemplatesText = Flags['DynamicParts'], Snippets['DynamicParts'], Snippets['StaticParts'], Snippets['Templates']
FileLower = File.lower()
PagePath = f"{OutDir}/{StripExt(File)}.html"
LightRun = False if LimitFiles == False or File in LimitFiles else True
if FileLower.endswith(FileExtensions['Markdown']):
Content = markdown(PagePostprocessor('md', Content, Meta), extensions=MarkdownExts)
elif FileLower.endswith(('.pug')):
Content = PagePostprocessor('pug', ReadFile(PagePath), Meta)
elif FileLower.endswith(('.txt')):
Content = '<pre>' + html.escape(Content) + '</pre>'
elif FileLower.endswith(FileExtensions['HTML']):
Content = ReadFile(PagePath)
if LightRun:
HTMLPagesList = None
else:
TemplateMeta = TemplatePreprocessor(TemplatesText[Meta['Template']])
HTMLPagesList = GetHTMLPagesList(
Pages=Pages,
BlogName=BlogName,
SiteRoot=SiteRoot,
PathPrefix=GetPathLevels(File),
Unite=ConfMenu,
Type='Page',
For='Menu',
MarkdownExts=MarkdownExts,
MenuStyle=TemplateMeta['MenuStyle'])
HTML, ContentHTML, Description, Image = PatchHTML(
File=File,
HTML=TemplatesText[Meta['Template']],
StaticPartsText=StaticPartsText,
DynamicParts=DynamicParts,
DynamicPartsText=DynamicPartsText,
HTMLPagesList=HTMLPagesList,
PagePath=PagePath[len(f"{OutDir}/"):],
Content=Content,
Titles=Titles,
Meta=Meta,
SiteDomain=SiteDomain,
SiteRoot=SiteRoot,
SiteName=SiteName,
BlogName=BlogName,
FolderRoots=FolderRoots,
Categories=Categories,
SiteLang=SiteLang,
Locale=Locale,
LightRun=LightRun)
HTML = ReplWithEsc(HTML, f"<staticoso:Feed>", GetHTMLPagesList(
Limit=Flags['FeedEntries'],
Type='Post',
Category=None if Flags['FeedCategoryFilter'] == '*' else Flags['FeedCategoryFilter'],
Pages=Pages,
BlogName=BlogName,
SiteRoot=SiteRoot,
PathPrefix=GetPathLevels(File),
For='Categories',
MarkdownExts=MarkdownExts,
MenuStyle='Flat',
ShowPaths=False))
if 'staticoso:DirectoryList:' in HTML: # Reduce risk of unnecessary cycles
for Line in HTML.splitlines():
Line = Line.lstrip().rstrip()
if Line.startswith('<staticoso:DirectoryList:') and Line.endswith('>'):
Path = Line[len('<staticoso:DirectoryList:'):-1]
DirectoryList = GetHTMLPagesList(
CallbackFile=File,
Pages=Pages,
BlogName=BlogName,
SiteRoot=SiteRoot,
PathPrefix=GetPathLevels(File),
PathFilter=Path,
For='Categories',
MarkdownExts=MarkdownExts,
MenuStyle='Flat')
HTML = ReplWithEsc(HTML, f"<staticoso:DirectoryList:{Path}>", DirectoryList)
if Flags['MinifyOutput']:
if not LightRun:
HTML = DoMinifyHTML(HTML, MinifyKeepComments)
ContentHTML = DoMinifyHTML(ContentHTML, MinifyKeepComments)
if Flags['NoScripts'] and ('<script' in ContentHTML.lower() or '<script' in HTML.lower()):
if not LightRun:
HTML = StripTags(HTML, ['script'])
ContentHTML = StripTags(ContentHTML, ['script'])
if ImgAltToTitle or ImgTitleToAlt:
if not LightRun:
HTML = WriteImgAltAndTitle(HTML, ImgAltToTitle, ImgTitleToAlt)
ContentHTML = WriteImgAltAndTitle(ContentHTML, ImgAltToTitle, ImgTitleToAlt)
if Flags['HTMLFixPre']:
if not LightRun:
HTML = DoHTMLFixPre(HTML)
ContentHTML = DoHTMLFixPre(ContentHTML)
if LightRun:
SlimHTML = None
else:
SlimHTML = HTMLPagesList + ContentHTML
if not LightRun:
WriteFile(PagePath, HTML)
if not LightRun and 'htmljournal' in ContentHTML.lower(): # Avoid extra cycles
HTML, _, _, _ = PatchHTML(
File=File,
HTML=TemplatesText[Meta['Template']],
StaticPartsText=StaticPartsText,
DynamicParts=DynamicParts,
DynamicPartsText=DynamicPartsText,
HTMLPagesList=HTMLPagesList,
PagePath=f'{StripExt(File)}.Journal.html',
Content=MakeHTMLJournal(Flags, Locale, f'{StripExt(File)}.html', ContentHTML),
Titles='',
Meta=Meta,
SiteDomain=SiteDomain,
SiteRoot=SiteRoot,
SiteName=SiteName,
BlogName=BlogName,
FolderRoots=FolderRoots,
Categories=Categories,
SiteLang=SiteLang,
Locale=Locale,
LightRun=LightRun)
if Flags["JournalRedirect"]:
HTML = HTML.replace('</head>', f"""<meta http-equiv="refresh" content="0; url='./{PagePath.split('''/''')[-1]}'"></head>""")
WriteFile(StripExt(PagePath)+'.Journal.html', HTML)
return [File, Content, Titles, Meta, ContentHTML, SlimHTML, Description, Image]
def MultiprocPagePreprocessor(d):
PrintProcPercentDots(d['Process'], 2)
return PagePreprocessor(d['Path'], d['TempPath'], d['Type'], d['Template'], d['SiteRoot'], d['GlobalMacros'], d['CategoryUncategorized'], d['LightRun'])
def MultiprocHandlePage(d):
PrintProcPercentDots(d['Process'])
return HandlePage(d['Flags'], d['Page'], d['Pages'], d['Categories'], d['LimitFiles'], d['Snippets'], d['ConfMenu'], d['Locale'])
def MakeSite(Flags, LimitFiles, Snippets, ConfMenu, GlobalMacros, Locale, Threads):
PagesPaths, PostsPaths, Pages, MadePages, Categories = [], [], [], [], {}
PoolSize = cpu_count() if Threads <= 0 else Threads
OutDir, MarkdownExts, Sorting = Flags['OutDir'], Flags['MarkdownExts'], Flags['Sorting']
SiteName, BlogName, SiteTagline = Flags['SiteName'], Flags['BlogName'], Flags['SiteTagline']
SiteTemplate, SiteLang = Flags['SiteTemplate'], Flags['SiteLang']
SiteDomain, SiteRoot, FolderRoots = Flags['SiteDomain'], Flags['SiteRoot'], Flags['FolderRoots']
AutoCategories, CategoryUncategorized = Flags['CategoriesAutomatic'], Flags['CategoriesUncategorized']
ImgAltToTitle, ImgTitleToAlt = Flags['ImgAltToTitle'], Flags['ImgTitleToAlt']
DynamicParts, DynamicPartsText, StaticPartsText, TemplatesText = Flags['DynamicParts'], Snippets['DynamicParts'], Snippets['StaticParts'], Snippets['Templates']
for Ext in FileExtensions['Pages']:
for File in Path('Pages').rglob(f"*.{Ext}"):
PagesPaths += [FileToStr(File, 'Pages/')]
for File in Path('Posts').rglob(f"*.{Ext}"):
PostsPaths += [FileToStr(File, 'Posts/')]
logging.info(f"Pages Found: {len(PagesPaths+PostsPaths)}")
PagesPaths = FileNameDateSort(PagesPaths)
if Sorting['Pages'] == 'Inverse':
PagesPaths.reverse()
PostsPaths = FileNameDateSort(PostsPaths)
if Sorting['Posts'] == 'Inverse':
PostsPaths.reverse()
logging.info("Preprocessing Source Pages")
MultiprocPages = []
for Type in ['Page', 'Post']:
if Type == 'Page':
Files = PagesPaths
PathPrefix = ''
elif Type == 'Post':
Files = PostsPaths
PathPrefix = 'Posts/'
for i,File in enumerate(Files):
TempPath = f"{PathPrefix}{File}"
LightRun = False if LimitFiles == False or TempPath in LimitFiles else True
MultiprocPages += [{'Process':{'Num':i, 'Count':len(Files)}, 'Path':f"{Type}s/{File}", 'TempPath':TempPath, 'Type':Type, 'Template':SiteTemplate, 'SiteRoot':SiteRoot, 'GlobalMacros':GlobalMacros, 'CategoryUncategorized':CategoryUncategorized, 'LightRun':LightRun}]
os.system('printf "["')
with Pool(PoolSize) as MultiprocPool:
Pages = MultiprocPool.map(MultiprocPagePreprocessor, MultiprocPages)
os.system('printf "]\n"') # Make newline after percentage dots
for File, Content, Titles, Meta in Pages:
for Cat in Meta['Categories']:
Categories.update({Cat:''})
PugCompileList(OutDir, Pages, LimitFiles)
if Categories:
logging.info("Generating Category Lists")
for Cat in Categories:
for Type in ('Page', 'Post'):
Categories[Cat] += GetHTMLPagesList(
Pages=Pages,
BlogName=BlogName,
SiteRoot=SiteRoot,
PathPrefix=GetPathLevels('Categories/'),
Type=Type,
Category=Cat,
For='Categories',
MarkdownExts=MarkdownExts,
MenuStyle='Flat')
if AutoCategories:
Dir = f"{OutDir}/Categories"
for Cat in Categories:
Exists = False
for File in Path(Dir).rglob(str(Cat)+'.*'):
Exists = True
break
if not Exists:
File = f"Categories/{Cat}.md"
FilePath = f"{OutDir}/{File}"
WriteFile(FilePath, CategoryPageTemplate.format(Name=Cat))
_, Content, Titles, Meta = PagePreprocessor(FilePath, FilePath, Type, SiteTemplate, SiteRoot, GlobalMacros, CategoryUncategorized, LightRun=LightRun)
Pages += [[File, Content, Titles, Meta]]
for i,e in enumerate(ConfMenu):
for File, Content, Titles, Meta in Pages:
File = StripExt(File)+'.html'
if e == File:
ConfMenu[i] = None
logging.info("Writing Pages")
MultiprocPages = []
for i,Page in enumerate(Pages):
MultiprocPages += [{'Process':{'Num':i, 'Count':len(Pages)}, 'Flags':Flags, 'Page':Page, 'Pages':Pages, 'Categories':Categories, 'LimitFiles':LimitFiles, 'Snippets':Snippets, 'ConfMenu':ConfMenu, 'Locale':Locale}]
os.system('printf "["')
with Pool(PoolSize) as MultiprocPool:
MadePages = MultiprocPool.map(MultiprocHandlePage, MultiprocPages)
os.system('printf "]\n"') # Make newline after percentage dots
# Do page transclusions here (?)
#while True:
# Operated = False
# for di,Dest in enumerate(MadePages):
# #print(Dest[0])
# #TempPath = f'{PathPrefix}{Dest["File"]}'
# #LightRun = False if LimitFiles == False or TempPath in LimitFiles else True
# #if not LightRun:
# if '[staticoso:Transclude:' in Dest[4] and (LimitFiles == False or f'{PathPrefix}{Dest[0]}' in LimitFiles):
# for Item in MadePages:
# SrcPrefix = '' if Item[0].startswith('Posts/') else 'Pages/'
# print(SrcPrefix, Item[0])
# if Item[0] != Dest[0] and f'[staticoso:Transclude:{SrcPrefix}{Item[0]}]' in Dest[4]:
# MadePages[di][4] = ReplWithEsc(Dest[4], f'<staticoso:Transclude:{Item[0]}>', Item[4])
# print(f'[staticoso:Transclude:{SrcPrefix}{Item[0]}]', Item[4])
# Operated = True
# if not Operated:
# break
return MadePages

View File

@@ -0,0 +1,19 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
from urllib.parse import quote as URLEncode
from Modules.Utils import *
def MakeSitemap(Flags, Pages):
Map = ''
Domain = Flags['SiteDomain'] + '/' if Flags['SiteDomain'] else ''
for File, Content, Titles, Meta, ContentHTML, SlimHTML, Description, Image in Pages:
File = f"{StripExt(File)}.html"
Map += Domain + URLEncode(File) + '\n'
WriteFile(f"{Flags['OutDir']}/sitemap.txt", Map)

177
App/Source/Modules/Utils.py Normal file
View File

@@ -0,0 +1,177 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
import json
import os
from datetime import datetime
from pathlib import Path
from Modules.Globals import *
def SureList(e):
return e if type(e) == list else [e]
# Get base directory path of the staticoso program
def staticosoBaseDir():
return f"{os.path.dirname(os.path.abspath(__file__))}/../../"
def ReadFile(p, m='r'):
try:
with open(p, m) as f:
return f.read()
except Exception:
logging.error(f"Error reading file {p}")
return None
def WriteFile(p, c, m='w'):
try:
with open(p, m) as f:
return f.write(c)
except Exception:
logging.error(f"[E] Error writing file {p}")
return False
def FileToStr(File, Truncate=''):
return str(File)[len(Truncate):]
# With shutil.copytree copy only folder struct, no files; https://stackoverflow.com/a/15664273
def IgnoreFiles(Dir, Files):
return [f for f in Files if os.path.isfile(os.path.join(Dir, f))]
def LoadFromDir(Dir, Matchs):
Contents = {}
Matchs = SureList(Matchs)
for Match in Matchs:
for File in Path(Dir).rglob(Match):
File = str(File)[len(Dir)+1:]
Contents.update({File: ReadFile(f"{Dir}/{File}")})
return Contents
def mkdirps(Dir):
return Path(Dir).mkdir(parents=True, exist_ok=True)
def StripExt(Path):
return ".".join(Path.split('.')[:-1])
def UndupeStr(Str, Known, Split):
while Str in Known:
Sections = Str.split(Split)
try:
Sections[-1] = str(int(Sections[-1]) + 1)
except ValueError:
Sections[-1] = Sections[-1] + str(Split) + '2'
Str = Split.join(Sections)
return Str
def DashifyStr(s, Limit=32):
Str = ''
for c in s[:Limit].replace('\n','-').replace('\t','-').replace(' ','-'):
if c.lower() in '0123456789qwfpbjluyarstgmneiozxcdvkh-':
Str += c
return '-' + Str
def GetPathLevels(Path, AsNum=False, Add=0, Sub=0):
n = Path.count('/') + Add - Sub
return n if AsNum else '../' * n
# https://stackoverflow.com/a/34445090
def FindAllIndex(Str, Sub):
i = Str.find(Sub)
while i != -1:
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)
for i,e in enumerate(Sects):
if i == 0:
New += e
elif i > 0:
if Sects[i-1].endswith(Esc*2):
New = New[:-1]
New += Repl + e
elif Sects[i-1].endswith(Esc):
New = New[:-1]
New += Find + e
else:
New += Repl + e
return New
def DictReplWithEsc(Str:str, Dict:dict, Esc:str='\\'):
for Item in Dict:
Str = ReplWithEsc(Str, Item, Dict[Item], Esc='\\')
return Str
def WrapDictReplWithEsc(Str:str, Dict:dict, Wraps:list=[], Esc:str='\\'):
NewDict = {}
for Item in Dict:
for Wrap in Wraps:
NewDict.update({f'{Wrap[0]}{Item}{Wrap[1]}': Dict[Item]})
return DictReplWithEsc(Str, NewDict, Esc)
def NumsFromFileName(Path):
Name = Path.split('/')[-1]
Split = len(Name)
for i,e in enumerate(Name):
if e.lower() in 'qwfpbjluyarstgmneiozxcdvkh':
return Name[:i]
return Path
def RevSort(List):
List.sort()
List.reverse()
return List
def FileNameDateSort(Old): # TODO: Test this for files not starting with date, and dated folders
New = []
if Old:
Old.sort()
New.insert(0, Old[0])
for i,e in enumerate(Old):
if i == 0:
continue
Done = False
for j,f in enumerate(New):
if NumsFromFileName(e) != e and NumsFromFileName(f) != f and NumsFromFileName(e) < NumsFromFileName(f):
New.insert(j, e)
Done = True
break
if not Done:
New += [e]
return New
def FirstRealItem(List):
return next(e for e in List if e)
def GetFullDate(Date):
if not Date:
return None
return datetime.strftime(datetime.strptime(Date, '%Y-%m-%d'), '%Y-%m-%dT%H:%M+00:00')
def LoadLocale(Lang):
Lang = Lang + '.json'
Folder = f'{staticosoBaseDir()}Locale/'
File = ReadFile(Folder + Lang)
if File:
return json.loads(File)
else:
return json.loads(ReadFile(Folder + 'en.json'))
def IsLightRun(File, LimitFiles):
return False if LimitFiles == False or File in LimitFiles else True
def PrintProcPercentDots(Proc, DivMult=1):
Div = 5 * DivMult # 100/5 = 20 chars
Num, Count = Proc['Num'], Proc['Count']
if int(((Num/Count)*100)/Div) != int((((Num+1)/Count)*100)/Div):
os.system('printf "="') # Using sys shell since for some reason print() without newline breaks here (doesn't print everytime)
return True
return False