Clean code

This commit is contained in:
octospacc 2022-07-14 20:38:45 +02:00
parent 24729b96f0
commit de9f0e832b
4 changed files with 424 additions and 404 deletions

View File

@ -15,15 +15,6 @@ from ast import literal_eval
from datetime import datetime
from pathlib import Path
# Our local Markdown patches conflict if the module is installed on the system, so first try to import from system
try:
from markdown import markdown
except ModuleNotFoundError:
from Libs.markdown import markdown
from Libs import htmlmin
from Libs.bs4 import BeautifulSoup
try:
from Modules.ActivityPub import *
ActivityPub = True
@ -33,13 +24,11 @@ except:
from Modules.Config import *
from Modules.Gemini import *
from Modules.Pug import *
from Modules.Markdown import *
from Modules.Site import *
from Modules.Sitemap import *
from Modules.Utils import *
Extensions = {
'Pages': ('md', 'pug')}
def ResetPublic():
for i in ('public', 'public.gmi'):
try:
@ -47,404 +36,14 @@ def ResetPublic():
except FileNotFoundError:
pass
def GetLevels(Path, AsNum=False, Add=0, Sub=0):
n = Path.count('/') + Add - Sub
return n if AsNum else '../' * n
def DashifyTitle(Title, Done=[]):
return UndupeStr(DashifyStr(Title), Done, '-')
def GetTitle(Meta, Titles, Prefer='MetaTitle', BlogName=None):
if Prefer == 'BodyTitle':
Title = Titles[0].lstrip('#') if Titles else Meta['Title'] if Meta['Title'] else 'Untitled'
elif Prefer == 'MetaTitle':
Title = Meta['Title'] if Meta['Title'] else Titles[0].lstrip('#') if Titles else 'Untitled'
elif Prefer == 'HTMLTitle':
Title = Meta['HTMLTitle'] if Meta['HTMLTitle'] else Meta['Title'] if Meta['Title'] else Titles[0].lstrip('#') if Titles else 'Untitled'
if Meta['Type'] == 'Post' and BlogName:
Title += ' - ' + BlogName
return Title
def GetDescription(Meta, BodyDescription, Prefer='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, BodyImage, Prefer='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 MakeLinkableTitle(Line, Title, DashTitle, Type):
if Type == 'md':
Index = Title.split(' ')[0].count('#')
return '<h{} id="{}">{}</h{}>'.format(Index, DashTitle, Title[Index+1:], Index)
elif Type == 'pug':
NewLine = ''
Index = Line.find('h')
NewLine += Line[:Index]
NewLine += "{}(id='{}')".format(Line[Index:Index+2], DashTitle)
NewLine += Line[Index+2:]
return NewLine
def MakeListTitle(File, Meta, Titles, Prefer, SiteRoot, BlogName, PathPrefix=''):
Title = GetTitle(Meta, Titles, Prefer, BlogName)
Link = False if Meta['Index'] == 'Unlinked' else True
if Link:
Title = '[{}]({})'.format(
Title,
'{}{}.html'.format(PathPrefix, StripExt(File)))
if Meta['Type'] == 'Post':
CreatedOn = Meta['CreatedOn'] if Meta['CreatedOn'] else '?'
Title = '[{}] {}'.format(CreatedOn, Title)
return Title
def FormatTitles(Titles):
# TODO: Somehow titles written in Pug can end up here and don't work, they should be handled
MDTitles, DashyTitles = '', []
for t in Titles:
n = t.split(' ')[0].count('#')
Heading = '- ' * n
Title = t.lstrip('#')
DashyTitle = DashifyTitle(Title, DashyTitles)
DashyTitles += [DashyTitle]
Title = '[{}](#{})'.format(Title, DashyTitle)
MDTitles += Heading + Title + '\n'
return markdown(MDTitles)
def Preprocessor(Path, SiteRoot):
File = ReadFile(Path)
Content, Titles, DashyTitles, Meta = '', [], [], {
'Template': 'Standard.html',
'Style': '',
'Type': '',
'Index': 'True',
'Title': '',
'HTMLTitle': '',
'Description': '',
'Image': '',
'Categories': [],
'CreatedOn': '',
'EditedOn': '',
'Order': None}
for l in File.splitlines():
ls = l.lstrip()
if ls.startswith('// '):
lss = ls[3:]
for Item in ('Template', 'Type', 'Index', 'Title', 'HTMLTitle', 'Description', 'Image', 'CreatedOn', 'EditedOn'):
ItemText = '{}: '.format(Item)
if lss.startswith(ItemText):
Meta[Item] = lss[len(ItemText):]
if lss.startswith('Categories: '):
for i in lss[len('Categories: '):].split(' '):
Meta['Categories'] += [i]
elif lss.startswith('Background: '):
Meta['Style'] += "#MainBox{Background:" + lss[len('Background: '):] + ";} "
elif lss.startswith('Style: '):
Meta['Style'] += lss[len('Style: '):] + ' '
elif lss.startswith('Order: '):
Meta['Order'] = int(lss[len('Order: '):])
else:
if Path.endswith('.md'):
if ls.startswith('#'):
DashTitle = DashifyTitle(l.lstrip('#'), DashyTitles)
DashyTitles += [DashTitle]
Titles += [l]
Content += MakeLinkableTitle(l, ls, DashTitle, 'md') + '\n'
else:
Content += l + '\n'
elif Path.endswith('.pug'):
if ls.startswith(('h1', 'h2', 'h3', 'h4', 'h5', 'h6')):
if ls[2:].startswith(("(class='NoTitle", '(class="NoTitle')):
Content += l + '\n'
else:
Title = '#'*int(ls[1]) + str(ls[3:])
DashTitle = DashifyTitle(Title.lstrip('#'), DashyTitles)
DashyTitles += [DashTitle]
Titles += [Title]
# TODO: We should handle headers that for any reason already have parenthesis
if ls[2:] == '(':
Content += l + '\n'
else:
Content += MakeLinkableTitle(l, Title, DashTitle, 'pug') + '\n'
else:
Content += l + '\n'
return Content, Titles, Meta
def MakeContentHeader(Meta, Locale, Categories=''):
Header = ''
for i in ['CreatedOn', 'EditedOn']:
if Meta[i]:
Header += '{} {} \n'.format(Locale[i], Meta[i])
if Categories:
Header += '{}: {} \n'.format(Locale['Categories'], Categories)
return markdown(Header)
def MakeCategoryLine(File, Meta):
Categories = ''
if Meta['Categories']:
for i in Meta['Categories']:
Categories += '[{}]({}{}.html) '.format(i, GetLevels(File) + 'Categories/', i)
return Categories
def PatchHTML(File, HTML, PartsText, ContextParts, ContextPartsText, HTMLPagesList, PagePath, Content, Titles, Meta, SiteRoot, SiteName, BlogName, FolderRoots, Categories, SiteLang, Locale):
HTMLTitles = FormatTitles(Titles)
BodyDescription, BodyImage = '', ''
Parse = BeautifulSoup(Content, 'html.parser')
if not BodyDescription and Parse.p:
BodyDescription = Parse.p.get_text()[:150].replace('\n', ' ').replace('"', "'") + '...'
if not BodyImage and Parse.img and Parse.img['src']:
BodyImage = Parse.img['src']
Title = GetTitle(Meta, Titles, 'MetaTitle', BlogName)
Description = GetDescription(Meta, BodyDescription, 'MetaDescription')
Image = GetImage(Meta, BodyImage, 'MetaImage')
for Line in HTML.splitlines():
Line = Line.lstrip().rstrip()
if Line.startswith('[HTML:ContextPart:') and Line.endswith(']'):
Path = Line[len('[HTML:ContextPart:'):-1]
Section = Path.split('/')[-1]
if Section in ContextParts:
Part = ContextParts[Section]
Text = ''
if type(Part) == list:
for i in Part:
Text += ContextPartsText['{}/{}'.format(Path, i)] + '\n'
elif type(Part) == str:
Text = ContextPartsText['{}/{}'.format(Path, Part)]
else:
Text = ''
HTML = HTML.replace('[HTML:ContextPart:{}]'.format(Path), Text)
for i in PartsText:
HTML = HTML.replace('[HTML:Part:{}]'.format(i), PartsText[i])
HTML = ReplWithEsc(HTML, '[HTML:Site:Menu]', HTMLPagesList)
HTML = ReplWithEsc(HTML, '[HTML:Page:Lang]', SiteLang)
HTML = ReplWithEsc(HTML, '[HTML:Page:Chapters]', HTMLTitles)
HTML = ReplWithEsc(HTML, '[HTML:Page:Title]', Title)
HTML = ReplWithEsc(HTML, '[HTML:Page:Description]', Description)
HTML = ReplWithEsc(HTML, '[HTML:Page:Image]', Image)
HTML = ReplWithEsc(HTML, '[HTML:Page:Path]', PagePath)
HTML = ReplWithEsc(HTML, '[HTML:Page:Style]', Meta['Style'])
HTML = ReplWithEsc(HTML, '[HTML:Page:Content]', Content)
HTML = ReplWithEsc(HTML, '[HTML:Page:ContentHeader]', MakeContentHeader(Meta, Locale, MakeCategoryLine(File, Meta)))
HTML = ReplWithEsc(HTML, '[HTML:Site:Name]', SiteName)
HTML = ReplWithEsc(HTML, '[HTML:Site:AbsoluteRoot]', SiteRoot)
HTML = ReplWithEsc(HTML, '[HTML:Site:RelativeRoot]', GetLevels(PagePath))
for i in FolderRoots:
HTML = HTML.replace('[HTML:Folder:{}:AbsoluteRoot]'.format(i), FolderRoots[i])
for i in Categories:
HTML = HTML.replace('<span>[HTML:Category:{}]</span>'.format(i), Categories[i])
# TODO: Clean this doubling?
ContentHTML = Content
ContentHTML = ContentHTML.replace('[HTML:Site:AbsoluteRoot]', SiteRoot)
ContentHTML = ContentHTML.replace('[HTML:Site:RelativeRoot]', GetLevels(PagePath))
for i in FolderRoots:
ContentHTML = ContentHTML.replace('[HTML:Folder:{}:AbsoluteRoot]'.format(i), FolderRoots[i])
for i in Categories:
ContentHTML = ContentHTML.replace('<span>[HTML:Category:{}]</span>'.format(i), Categories[i])
SlimHTML = HTMLPagesList + ContentHTML
return HTML, ContentHTML, SlimHTML, Description, Image
def OrderPages(Old):
New, NoOrder, Max = [], [], 0
for i,e in enumerate(Old):
Curr = e[3]['Order']
if Curr:
if Curr > Max:
Max = Curr
else:
NoOrder += [e]
for i in range(Max+1):
New += [[]]
for i,e in enumerate(Old):
Curr = e[3]['Order']
if Curr:
New[Curr] = e
while [] in New:
New.remove([])
return New + NoOrder
def CanIndex(Index, For):
if Index in ('False', 'None'):
return False
elif Index in ('True', 'All', 'Unlinked'):
return True
else:
return True if Index == For else False
def GetHTMLPagesList(Pages, BlogName, SiteRoot, PathPrefix, Type='Page', Category=None, For='Menu'):
List, ToPop, LastParent = '', [], []
IndexPages = Pages.copy()
for e in IndexPages:
if e[3]['Index'] == 'False' or e[3]['Index'] == 'None':
IndexPages.remove(e)
for i,e in enumerate(IndexPages):
if e[3]['Type'] != Type:
ToPop += [i]
ToPop = RevSort(ToPop)
for i in ToPop:
IndexPages.pop(i)
if Type == 'Page':
IndexPages = OrderPages(IndexPages)
for File, Content, Titles, Meta in IndexPages:
if Meta['Type'] == Type and CanIndex(Meta['Index'], For) and GetTitle(Meta, Titles, 'HTMLTitle', BlogName) != 'Untitled' and (not Category or Category in Meta['Categories']):
n = File.count('/') + 1
if n > 1:
CurParent = File.split('/')[:-1]
for i,s in enumerate(CurParent):
if LastParent != CurParent:
LastParent = CurParent
Levels = '- ' * (n-1+i)
if StripExt(File).endswith('index'):
Title = MakeListTitle(File, Meta, Titles, 'HTMLTitle', SiteRoot, BlogName, PathPrefix)
else:
Title = CurParent[n-2+i]
List += Levels + Title + '\n'
if not (n > 1 and StripExt(File).endswith('index')):
Levels = '- ' * n
Title = MakeListTitle(File, Meta, Titles, 'HTMLTitle', SiteRoot, BlogName, PathPrefix)
List += Levels + Title + '\n'
return markdown(List)
def DelTmp():
for Ext in Extensions['Pages']:
for Ext in FileExtensions['Pages']:
for File in Path('public').rglob('*.{}'.format(Ext)):
os.remove(File)
for Dir in ('public', 'public.gmi'):
for File in Path(Dir).rglob('*.tmp'):
os.remove(File)
def RevSort(List):
List.sort()
List.reverse()
return List
def DoMinify(HTML):
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(TemplatesText, PartsText, ContextParts, ContextPartsText, SiteName, BlogName, SiteTagline, SiteDomain, SiteRoot, FolderRoots, SiteLang, Locale, Minify, Sorting, MarkdownExts, AutoCategories):
PagesPaths, PostsPaths, Pages, MadePages, Categories = [], [], [], [], {}
for Ext in Extensions['Pages']:
for File in Path('Pages').rglob('*.{}'.format(Ext)):
PagesPaths += [FileToStr(File, 'Pages/')]
for File in Path('Posts').rglob('*.{}'.format(Ext)):
PostsPaths += [FileToStr(File, 'Posts/')]
if Sorting['Pages'] == 'Standard':
PagesPaths.sort()
elif Sorting['Pages'] == 'Inverse':
PagesPaths = RevSort(PagesPaths)
if Sorting['Posts'] == 'Standard':
PostsPaths.sort()
elif Sorting['Posts'] == 'Inverse':
PostsPaths = RevSort(PostsPaths)
print("[I] Preprocessing Source Pages")
for Type in ['Page', 'Post']:
if Type == 'Page':
Files = PagesPaths
elif Type == 'Post':
Files = PostsPaths
for File in Files:
Content, Titles, Meta = Preprocessor('{}s/{}'.format(Type, File), SiteRoot)
if Type != 'Page':
File = Type + 's/' + File
if not Meta['Type']:
Meta['Type'] = Type
Pages += [[File, Content, Titles, Meta]]
for Cat in Meta['Categories']:
Categories.update({Cat:''})
PugCompileList(Pages)
if Categories:
print("[I] Generating Category Lists")
for Cat in Categories:
for Type in ('Page', 'Post'):
Categories[Cat] += GetHTMLPagesList(
Pages=Pages,
BlogName=BlogName,
SiteRoot=SiteRoot,
PathPrefix=GetLevels('Categories/'),
Type=Type,
Category=Cat,
For='Categories')
if AutoCategories:
Dir = 'public/Categories'
for Cat in Categories:
Exists = False
for File in Path(Dir).rglob(str(Cat)+'.*'):
Exists = True
break
if not Exists:
File = 'Categories/{}.md'.format(Cat)
FilePath = 'public/{}'.format(File)
WriteFile(FilePath, """\
// Title: {Category}
// Type: Page
# {Category}
<div><span>[HTML:Category:{Category}]</span></div>
""".format(Category=Cat))
Content, Titles, Meta = Preprocessor(FilePath, SiteRoot)
Pages += [[File, Content, Titles, Meta]]
print("[I] Writing Pages")
for File, Content, Titles, Meta in Pages:
HTMLPagesList = GetHTMLPagesList(
Pages=Pages,
BlogName=BlogName,
SiteRoot=SiteRoot,
PathPrefix=GetLevels(File),
Type='Page',
For='Menu')
PagePath = 'public/{}.html'.format(StripExt(File))
if File.endswith('.md'):
Content = markdown(Content, extensions=MarkdownExts)
elif File.endswith('.pug'):
Content = ReadFile(PagePath)
HTML, ContentHTML, SlimHTML, Description, Image = PatchHTML(
File=File,
HTML=TemplatesText[Meta['Template']],
PartsText=PartsText,
ContextParts=ContextParts,
ContextPartsText=ContextPartsText,
HTMLPagesList=HTMLPagesList,
PagePath=PagePath[len('public/'):],
Content=Content,
Titles=Titles,
Meta=Meta,
SiteRoot=SiteRoot,
SiteName=SiteName,
BlogName=BlogName,
FolderRoots=FolderRoots,
Categories=Categories,
SiteLang=SiteLang,
Locale=Locale)
if Minify:
HTML = DoMinify(HTML)
WriteFile(PagePath, HTML)
MadePages += [[File, Content, Titles, Meta, ContentHTML, SlimHTML, Description, Image]]
return MadePages
def SetSorting(Sorting):
Default = {
'Pages':'Standard',

View File

@ -0,0 +1,14 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
# Our local Markdown patches conflict if the module is installed on the system, so first try to import from system
try:
from markdown import markdown
except ModuleNotFoundError:
from Libs.markdown import markdown

395
Source/Modules/Site.py Normal file
View File

@ -0,0 +1,395 @@
""" ================================= |
| This file is part of |
| staticoso |
| Just a simple Static Site Generator |
| |
| Licensed under the AGPLv3 license |
| Copyright (C) 2022, OctoSpacc |
| ================================= """
from Libs import htmlmin
from Libs.bs4 import BeautifulSoup
from Modules.Markdown import *
from Modules.Pug import *
from Modules.Utils import *
def DashifyTitle(Title, Done=[]):
return UndupeStr(DashifyStr(Title), Done, '-')
def MakeLinkableTitle(Line, Title, DashTitle, Type):
if Type == 'md':
Index = Title.split(' ')[0].count('#')
return '<h{} id="{}">{}</h{}>'.format(Index, DashTitle, Title[Index+1:], Index)
elif Type == 'pug':
NewLine = ''
Index = Line.find('h')
NewLine += Line[:Index]
NewLine += "{}(id='{}')".format(Line[Index:Index+2], DashTitle)
NewLine += Line[Index+2:]
return NewLine
def GetTitle(Meta, Titles, Prefer='MetaTitle', BlogName=None):
if Prefer == 'BodyTitle':
Title = Titles[0].lstrip('#') if Titles else Meta['Title'] if Meta['Title'] else 'Untitled'
elif Prefer == 'MetaTitle':
Title = Meta['Title'] if Meta['Title'] else Titles[0].lstrip('#') if Titles else 'Untitled'
elif Prefer == 'HTMLTitle':
Title = Meta['HTMLTitle'] if Meta['HTMLTitle'] else Meta['Title'] if Meta['Title'] else Titles[0].lstrip('#') if Titles else 'Untitled'
if Meta['Type'] == 'Post' and BlogName:
Title += ' - ' + BlogName
return Title
def GetDescription(Meta, BodyDescription, Prefer='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, BodyImage, Prefer='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, Locale, Categories=''):
Header = ''
for i in ['CreatedOn', 'EditedOn']:
if Meta[i]:
Header += '{} {} \n'.format(Locale[i], Meta[i])
if Categories:
Header += '{}: {} \n'.format(Locale['Categories'], Categories)
return markdown(Header)
def MakeCategoryLine(File, Meta):
Categories = ''
if Meta['Categories']:
for i in Meta['Categories']:
Categories += '[{}]({}{}.html) '.format(i, GetPathLevels(File) + 'Categories/', i)
return Categories
def GetHTMLPagesList(Pages, BlogName, SiteRoot, PathPrefix, Type='Page', Category=None, For='Menu'):
List, ToPop, LastParent = '', [], []
IndexPages = Pages.copy()
for e in IndexPages:
if e[3]['Index'] == 'False' or e[3]['Index'] == 'None':
IndexPages.remove(e)
for i,e in enumerate(IndexPages):
if e[3]['Type'] != Type:
ToPop += [i]
ToPop = RevSort(ToPop)
for i in ToPop:
IndexPages.pop(i)
if Type == 'Page':
IndexPages = OrderPages(IndexPages)
for File, Content, Titles, Meta in IndexPages:
if Meta['Type'] == Type and CanIndex(Meta['Index'], For) and GetTitle(Meta, Titles, 'HTMLTitle', BlogName) != 'Untitled' and (not Category or Category in Meta['Categories']):
n = File.count('/') + 1
if n > 1:
CurParent = File.split('/')[:-1]
for i,s in enumerate(CurParent):
if LastParent != CurParent:
LastParent = CurParent
Levels = '- ' * (n-1+i)
if StripExt(File).endswith('index'):
Title = MakeListTitle(File, Meta, Titles, 'HTMLTitle', SiteRoot, BlogName, PathPrefix)
else:
Title = CurParent[n-2+i]
List += Levels + Title + '\n'
if not (n > 1 and StripExt(File).endswith('index')):
Levels = '- ' * n
Title = MakeListTitle(File, Meta, Titles, 'HTMLTitle', SiteRoot, BlogName, PathPrefix)
List += Levels + Title + '\n'
return markdown(List)
def Preprocessor(Path, SiteRoot):
File = ReadFile(Path)
Content, Titles, DashyTitles, Meta = '', [], [], {
'Template': 'Standard.html',
'Style': '',
'Type': '',
'Index': 'True',
'Title': '',
'HTMLTitle': '',
'Description': '',
'Image': '',
'Categories': [],
'CreatedOn': '',
'EditedOn': '',
'Order': None}
for l in File.splitlines():
ls = l.lstrip()
if ls.startswith('// '):
lss = ls[3:]
for Item in ('Template', 'Type', 'Index', 'Title', 'HTMLTitle', 'Description', 'Image', 'CreatedOn', 'EditedOn'):
ItemText = '{}: '.format(Item)
if lss.startswith(ItemText):
Meta[Item] = lss[len(ItemText):]
if lss.startswith('Categories: '):
for i in lss[len('Categories: '):].split(' '):
Meta['Categories'] += [i]
elif lss.startswith('Background: '):
Meta['Style'] += "#MainBox{Background:" + lss[len('Background: '):] + ";} "
elif lss.startswith('Style: '):
Meta['Style'] += lss[len('Style: '):] + ' '
elif lss.startswith('Order: '):
Meta['Order'] = int(lss[len('Order: '):])
else:
if Path.endswith('.md'):
if ls.startswith('#'):
DashTitle = DashifyTitle(l.lstrip('#'), DashyTitles)
DashyTitles += [DashTitle]
Titles += [l]
Content += MakeLinkableTitle(l, ls, DashTitle, 'md') + '\n'
else:
Content += l + '\n'
elif Path.endswith('.pug'):
if ls.startswith(('h1', 'h2', 'h3', 'h4', 'h5', 'h6')):
if ls[2:].startswith(("(class='NoTitle", '(class="NoTitle')):
Content += l + '\n'
else:
Title = '#'*int(ls[1]) + str(ls[3:])
DashTitle = DashifyTitle(Title.lstrip('#'), DashyTitles)
DashyTitles += [DashTitle]
Titles += [Title]
# TODO: We should handle headers that for any reason already have parenthesis
if ls[2:] == '(':
Content += l + '\n'
else:
Content += MakeLinkableTitle(l, Title, DashTitle, 'pug') + '\n'
else:
Content += l + '\n'
return Content, Titles, Meta
def MakeListTitle(File, Meta, Titles, Prefer, SiteRoot, BlogName, PathPrefix=''):
Title = GetTitle(Meta, Titles, Prefer, BlogName)
Link = False if Meta['Index'] == 'Unlinked' else True
if Link:
Title = '[{}]({})'.format(
Title,
'{}{}.html'.format(PathPrefix, StripExt(File)))
if Meta['Type'] == 'Post':
CreatedOn = Meta['CreatedOn'] if Meta['CreatedOn'] else '?'
Title = '[{}] {}'.format(CreatedOn, Title)
return Title
def FormatTitles(Titles):
# TODO: Somehow titles written in Pug can end up here and don't work, they should be handled
MDTitles, DashyTitles = '', []
for t in Titles:
n = t.split(' ')[0].count('#')
Heading = '- ' * n
Title = t.lstrip('#')
DashyTitle = DashifyTitle(Title, DashyTitles)
DashyTitles += [DashyTitle]
Title = '[{}](#{})'.format(Title, DashyTitle)
MDTitles += Heading + Title + '\n'
return markdown(MDTitles)
def OrderPages(Old):
New, NoOrder, Max = [], [], 0
for i,e in enumerate(Old):
Curr = e[3]['Order']
if Curr:
if Curr > Max:
Max = Curr
else:
NoOrder += [e]
for i in range(Max+1):
New += [[]]
for i,e in enumerate(Old):
Curr = e[3]['Order']
if Curr:
New[Curr] = e
while [] in New:
New.remove([])
return New + NoOrder
def CanIndex(Index, For):
if Index in ('False', 'None'):
return False
elif Index in ('True', 'All', 'Unlinked'):
return True
else:
return True if Index == For else False
def PatchHTML(File, HTML, PartsText, ContextParts, ContextPartsText, HTMLPagesList, PagePath, Content, Titles, Meta, SiteRoot, SiteName, BlogName, FolderRoots, Categories, SiteLang, Locale):
HTMLTitles = FormatTitles(Titles)
BodyDescription, BodyImage = '', ''
Parse = BeautifulSoup(Content, 'html.parser')
if not BodyDescription and Parse.p:
BodyDescription = Parse.p.get_text()[:150].replace('\n', ' ').replace('"', "'") + '...'
if not BodyImage and Parse.img and Parse.img['src']:
BodyImage = Parse.img['src']
Title = GetTitle(Meta, Titles, 'MetaTitle', BlogName)
Description = GetDescription(Meta, BodyDescription, 'MetaDescription')
Image = GetImage(Meta, BodyImage, 'MetaImage')
for Line in HTML.splitlines():
Line = Line.lstrip().rstrip()
if Line.startswith('[HTML:ContextPart:') and Line.endswith(']'):
Path = Line[len('[HTML:ContextPart:'):-1]
Section = Path.split('/')[-1]
if Section in ContextParts:
Part = ContextParts[Section]
Text = ''
if type(Part) == list:
for i in Part:
Text += ContextPartsText['{}/{}'.format(Path, i)] + '\n'
elif type(Part) == str:
Text = ContextPartsText['{}/{}'.format(Path, Part)]
else:
Text = ''
HTML = HTML.replace('[HTML:ContextPart:{}]'.format(Path), Text)
for i in PartsText:
HTML = HTML.replace('[HTML:Part:{}]'.format(i), PartsText[i])
HTML = ReplWithEsc(HTML, '[HTML:Site:Menu]', HTMLPagesList)
HTML = ReplWithEsc(HTML, '[HTML:Page:Lang]', SiteLang)
HTML = ReplWithEsc(HTML, '[HTML:Page:Chapters]', HTMLTitles)
HTML = ReplWithEsc(HTML, '[HTML:Page:Title]', Title)
HTML = ReplWithEsc(HTML, '[HTML:Page:Description]', Description)
HTML = ReplWithEsc(HTML, '[HTML:Page:Image]', Image)
HTML = ReplWithEsc(HTML, '[HTML:Page:Path]', PagePath)
HTML = ReplWithEsc(HTML, '[HTML:Page:Style]', Meta['Style'])
HTML = ReplWithEsc(HTML, '[HTML:Page:Content]', Content)
HTML = ReplWithEsc(HTML, '[HTML:Page:ContentHeader]', MakeContentHeader(Meta, Locale, MakeCategoryLine(File, Meta)))
HTML = ReplWithEsc(HTML, '[HTML:Site:Name]', SiteName)
HTML = ReplWithEsc(HTML, '[HTML:Site:AbsoluteRoot]', SiteRoot)
HTML = ReplWithEsc(HTML, '[HTML:Site:RelativeRoot]', GetPathLevels(PagePath))
for i in FolderRoots:
HTML = HTML.replace('[HTML:Folder:{}:AbsoluteRoot]'.format(i), FolderRoots[i])
for i in Categories:
HTML = HTML.replace('<span>[HTML:Category:{}]</span>'.format(i), Categories[i])
# TODO: Clean this doubling?
ContentHTML = Content
ContentHTML = ContentHTML.replace('[HTML:Site:AbsoluteRoot]', SiteRoot)
ContentHTML = ContentHTML.replace('[HTML:Site:RelativeRoot]', GetPathLevels(PagePath))
for i in FolderRoots:
ContentHTML = ContentHTML.replace('[HTML:Folder:{}:AbsoluteRoot]'.format(i), FolderRoots[i])
for i in Categories:
ContentHTML = ContentHTML.replace('<span>[HTML:Category:{}]</span>'.format(i), Categories[i])
SlimHTML = HTMLPagesList + ContentHTML
return HTML, ContentHTML, SlimHTML, Description, Image
def DoMinify(HTML):
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(TemplatesText, PartsText, ContextParts, ContextPartsText, SiteName, BlogName, SiteTagline, SiteDomain, SiteRoot, FolderRoots, SiteLang, Locale, Minify, Sorting, MarkdownExts, AutoCategories):
PagesPaths, PostsPaths, Pages, MadePages, Categories = [], [], [], [], {}
for Ext in FileExtensions['Pages']:
for File in Path('Pages').rglob('*.{}'.format(Ext)):
PagesPaths += [FileToStr(File, 'Pages/')]
for File in Path('Posts').rglob('*.{}'.format(Ext)):
PostsPaths += [FileToStr(File, 'Posts/')]
if Sorting['Pages'] == 'Standard':
PagesPaths.sort()
elif Sorting['Pages'] == 'Inverse':
PagesPaths = RevSort(PagesPaths)
if Sorting['Posts'] == 'Standard':
PostsPaths.sort()
elif Sorting['Posts'] == 'Inverse':
PostsPaths = RevSort(PostsPaths)
print("[I] Preprocessing Source Pages")
for Type in ['Page', 'Post']:
if Type == 'Page':
Files = PagesPaths
elif Type == 'Post':
Files = PostsPaths
for File in Files:
Content, Titles, Meta = Preprocessor('{}s/{}'.format(Type, File), SiteRoot)
if Type != 'Page':
File = Type + 's/' + File
if not Meta['Type']:
Meta['Type'] = Type
Pages += [[File, Content, Titles, Meta]]
for Cat in Meta['Categories']:
Categories.update({Cat:''})
PugCompileList(Pages)
if Categories:
print("[I] 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')
if AutoCategories:
Dir = 'public/Categories'
for Cat in Categories:
Exists = False
for File in Path(Dir).rglob(str(Cat)+'.*'):
Exists = True
break
if not Exists:
File = 'Categories/{}.md'.format(Cat)
FilePath = 'public/{}'.format(File)
WriteFile(FilePath, """\
// Title: {Category}
// Type: Page
# {Category}
<div><span>[HTML:Category:{Category}]</span></div>
""".format(Category=Cat))
Content, Titles, Meta = Preprocessor(FilePath, SiteRoot)
Pages += [[File, Content, Titles, Meta]]
print("[I] Writing Pages")
for File, Content, Titles, Meta in Pages:
HTMLPagesList = GetHTMLPagesList(
Pages=Pages,
BlogName=BlogName,
SiteRoot=SiteRoot,
PathPrefix=GetPathLevels(File),
Type='Page',
For='Menu')
PagePath = 'public/{}.html'.format(StripExt(File))
if File.endswith('.md'):
Content = markdown(Content, extensions=MarkdownExts)
elif File.endswith('.pug'):
Content = ReadFile(PagePath)
HTML, ContentHTML, SlimHTML, Description, Image = PatchHTML(
File=File,
HTML=TemplatesText[Meta['Template']],
PartsText=PartsText,
ContextParts=ContextParts,
ContextPartsText=ContextPartsText,
HTMLPagesList=HTMLPagesList,
PagePath=PagePath[len('public/'):],
Content=Content,
Titles=Titles,
Meta=Meta,
SiteRoot=SiteRoot,
SiteName=SiteName,
BlogName=BlogName,
FolderRoots=FolderRoots,
Categories=Categories,
SiteLang=SiteLang,
Locale=Locale)
if Minify:
HTML = DoMinify(HTML)
WriteFile(PagePath, HTML)
MadePages += [[File, Content, Titles, Meta, ContentHTML, SlimHTML, Description, Image]]
return MadePages

View File

@ -12,6 +12,9 @@ import os
from datetime import datetime
from pathlib import Path
FileExtensions = {
'Pages': ('md', 'pug')}
def ReadFile(p):
try:
with open(p, 'r') as f:
@ -63,6 +66,10 @@ def DashifyStr(s, Limit=32):
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)
@ -86,6 +93,11 @@ def ReplWithEsc(Str, Find, Repl, Esc='\\'):
New += Repl + e
return New
def RevSort(List):
List.sort()
List.reverse()
return List
def GetFullDate(Date):
if not Date:
return None