""" ================================= |
| 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.Config import *
from Modules.HTML import *
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 '{}'.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 BlogName and 'Blog' in Meta['Categories']:
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, Unite=[], Type='Page', Category=None, For='Menu', MarkdownExts=(), ShowPaths=True, Flatten=False):
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 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:
if Meta['Type'] == Type and CanIndex(Meta['Index'], For) and (not Category or Category in Meta['Categories']):
Depth = (File.count('/') + 1) if Meta['Order'] != 'Unite' else 1
if Depth > 1 and Meta['Order'] != 'Unite':
CurParent = File.split('/')[:-1]
for i,s in enumerate(CurParent):
if LastParent != CurParent:
LastParent = CurParent
Levels = '- ' * ((Depth-1+i) if not Flatten else 1)
if StripExt(File).endswith('index'):
Title = MakeListTitle(File, Meta, Titles, 'HTMLTitle', SiteRoot, BlogName, PathPrefix)
else:
Title = CurParent[Depth-2+i]
List += Levels + Title + '\n'
if not (Depth > 1 and StripExt(File).split('/')[-1] == 'index'):
Levels = '- ' * (Depth if not Flatten else 1)
if Meta['Order'] == 'Unite':
Title = File
else:
Title = MakeListTitle(File, Meta, Titles, 'HTMLTitle', SiteRoot, BlogName, PathPrefix)
List += Levels + Title + '\n'
return markdown(MarkdownHTMLEscape(List, MarkdownExts), extensions=MarkdownExts)
def Preprocessor(Path, SiteRoot, GlobalMacros):
File = ReadFile(Path)
Content, Titles, DashyTitles, HTMLTitlesFound, Macros, Meta = '', [], [], False, '', {
'Template': 'Standard.html',
'Style': '',
'Type': '',
'Index': 'True',
'Feed': 'True',
'Title': '',
'HTMLTitle': '',
'Description': '',
'Image': '',
'Macros': {},
'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', 'Feed', 'Title', 'HTMLTitle', 'Description', 'Image', 'CreatedOn', 'EditedOn'):
ItemText = '{}: '.format(Item)
if lss.startswith(ItemText):
Meta[Item] = lss[len(ItemText):]
if lss.startswith('$'):
Macros += lss[1:].lstrip() + '\n'
elif 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:
Headings = ('h1', 'h2', 'h3', 'h4', 'h5', 'h6')
if Path.endswith('.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'))
Content = str(Soup.prettify(formatter=None))
HTMLTitlesFound = True
elif Path.endswith('.md'):
if ls.startswith('#'):
DashTitle = DashifyTitle(l.lstrip('#'), DashyTitles)
DashyTitles += [DashTitle]
Titles += [l]
Content += MakeLinkableTitle(None, ls, DashTitle, 'md') + '\n'
else:
Content += l + '\n'
elif Path.endswith('.pug'):
if ls.startswith(Headings):
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'
if GlobalMacros:
Meta['Macros'].update(GlobalMacros)
Meta['Macros'].update(ReadConf(LoadConfStr('[Macros]\n' + Macros), 'Macros'))
return Content, Titles, Meta
def Postprocessor(FileType, Text, Meta):
for e in Meta['Macros']:
Text = ReplWithEsc(Text, f"[: {e} :]", f"[:{e}:]")
return Text
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, Flatten=False):
# 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 if not Flatten else 1)
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 = '', ''
Soup = BeautifulSoup(Content, 'html.parser')
if not BodyDescription and Soup.p:
BodyDescription = Soup.p.get_text()[:150].replace('\n', ' ').replace('"', "'") + '...'
if not BodyImage and Soup.img and Soup.img['src']:
BodyImage = Soup.img['src']
#Content = SquareFnrefs(Content)
Content = AddToTagStartEnd(Content, '