Reproog/novelWriter
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Adding non-breaking space support for editor and html, latex export

Browse Source
This commit is contained in:
Veronica K. B. Olsen
2019-10-29 14:49:11 +01:00
parent 146756a395
commit 489eae2e0d
10 changed files with 104 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nw/convert/file/html.py
+13 -12
View File
@@ -38,18 +38,19 @@ class HtmlFile(TextFile):
self.outFile.write("<!DOCTYPE html>\n")
self.outFile.write("<html>\n")
self.outFile.write("<head>\n")
self.outFile.write("<style>\n")
self.outFile.write(" #page {\n")
self.outFile.write(" margin: 40px auto;\n")
self.outFile.write(" max-width: 769px;\n")
self.outFile.write(" }\n")
self.outFile.write(" .comment {\n")
self.outFile.write(" background-color: #fbfabd;\n")
self.outFile.write(" border: 1px solid #b4b000;\n")
self.outFile.write(" margin: 10px 20px;\n")
self.outFile.write(" padding: 6px;\n")
self.outFile.write(" }\n")
self.outFile.write("</style>\n")
self.outFile.write(" <meta charset='utf-8'>\n")
self.outFile.write(" <style>\n")
self.outFile.write(" #page {\n")
self.outFile.write(" margin: 40px auto;\n")
self.outFile.write(" max-width: 769px;\n")
self.outFile.write(" }\n")
self.outFile.write(" .comment {\n")
self.outFile.write(" background-color: #fbfabd;\n")
self.outFile.write(" border: 1px solid #b4b000;\n")
self.outFile.write(" margin: 10px 20px;\n")
self.outFile.write(" padding: 6px;\n")
self.outFile.write(" }\n")
self.outFile.write(" </style>\n")
self.outFile.write("</head>\n")
self.outFile.write("<body>\n")
self.outFile.write("<article id='page'>\n")
nw/convert/file/text.py
+1
View File
@@ -138,6 +138,7 @@ class TextFile():
self.theConv.tokenizeText()
self.theConv.doHeaders()
self.theConv.doConvert()
self.theConv.doPostProcessing()
if self.theConv.theResult is not None and self.outFile is not None:
self.outFile.write(self.theConv.theResult)
nw/convert/text/tohtml.py
+8 -7
View File
@@ -15,6 +15,7 @@ import re
import nw
from nw.convert.tokenizer import Tokenizer
from nw.constants import nwUnicode
logger = logging.getLogger(__name__)
@@ -28,13 +29,13 @@ class ToHtml(Tokenizer):
Tokenizer.doAutoReplace(self)
repDict = {
"<" : "&lt;",
">" : "&gt;",
"&" : "&amp;",
"\u2013" : "&endash;",
"\u2014" : "$emdash;",
"\u2500" : "$emdash;",
"\u2026" : "&hellip;",
"<" : "&lt;",
">" : "&gt;",
"&" : "&amp;",
nwUnicode.U_ENDASH : nwUnicode.H_ENDASH,
nwUnicode.U_EMDASH : nwUnicode.H_EMDASH,
nwUnicode.U_HELLIP : nwUnicode.H_HELLIP,
nwUnicode.U_NBSP : nwUnicode.H_NBSP,
}
xRep = re.compile("|".join([re.escape(k) for k in repDict.keys()]), flags=re.DOTALL)
self.theText = xRep.sub(lambda x: repDict[x.group(0)], self.theText)
nw/convert/text/tolatex.py
+15
View File
@@ -16,6 +16,7 @@ import re
import nw
from nw.convert.tokenizer import Tokenizer
from nw.constants import nwUnicode
logger = logging.getLogger(__name__)
@@ -26,6 +27,20 @@ class ToLaTeX(Tokenizer):
self.texCodecFail = False
return
def doPostProcessing(self):
"""The latexcodec misses dashes and non-breaking spaces, so we do those here.
"""
repDict = {
nwUnicode.U_ENDASH : "--",
nwUnicode.U_EMDASH : "---",
nwUnicode.U_NBSP : "~",
}
xRep = re.compile("|".join([re.escape(k) for k in repDict.keys()]), flags=re.DOTALL)
self.theResult = xRep.sub(lambda x: repDict[x.group(0)], self.theResult)
return
def doConvert(self):
texTags = {
nw/convert/text/totext.py
+12
View File
@@ -16,6 +16,7 @@ import re
import nw
from nw.convert.tokenizer import Tokenizer
from nw.constants import nwUnicode
logger = logging.getLogger(__name__)
@@ -25,6 +26,17 @@ class ToText(Tokenizer):
Tokenizer.__init__(self, theProject, theParent)
return
def doAutoReplace(self):
Tokenizer.doAutoReplace(self)
repDict = {
nwUnicode.U_NBSP : " ",
}
xRep = re.compile("|".join([re.escape(k) for k in repDict.keys()]), flags=re.DOTALL)
self.theText = xRep.sub(lambda x: repDict[x.group(0)], self.theText)
return
def doConvert(self):
"""Converts the tokenized text into plain text.
"""
nw/convert/tokenizer.py
+3
View File
@@ -149,6 +149,9 @@ class Tokenizer():
self.theText = xRep.sub(lambda x: repDict[x.group(0)], self.theText)
return
def doPostProcessing(self):
return
def tokenizeText(self):
"""Scan the text for either lines starting with specific characters that indicate headers,
comments, commands etc, or just contains plain text. in the case of plain text, apply the