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

Merge branch 'main' into unicode_fix

Browse Source
This commit is contained in:
Veronica Berglyd Olsen
2025-07-05 14:17:16 +02:00
parent 57bed18ccf 7e2b95d390
commit 8067acdc1c
170 changed files with 5273 additions and 2593 deletions
Download Patch File Download Diff File Expand all files Collapse all files
novelwriter/formats/shared.py
+9 -1
View File
@@ -29,7 +29,15 @@ from enum import Flag, IntEnum
from PyQt6.QtGui import QColor
ESCAPES = {r"\*": "*", r"\~": "~", r"\_": "_", r"\[": "[", r"\]": "]", r"\ ": ""}
ESCAPES = {
r"\*": "*",
r"\~": "~",
r"\=": "=",
r"\_": "_",
r"\[": "[",
r"\]": "]",
r"\ ": "",
}
RX_ESC = re.compile("|".join([re.escape(k) for k in ESCAPES.keys()]), flags=re.DOTALL)
novelwriter/formats/todocx.py
+2 -2
View File
@@ -38,7 +38,7 @@ from novelwriter import __version__
from novelwriter.common import firstFloat, xmlElement, xmlSubElem
from novelwriter.constants import nwHeadFmt, nwStyles
from novelwriter.formats.shared import BlockFmt, BlockTyp, T_Formats, TextFmt, stripEscape
from novelwriter.formats.tokenizer import Tokenizer
from novelwriter.formats.tokenizer import COMMENT_BLOCKS, Tokenizer
from novelwriter.types import QtHexRgb
if TYPE_CHECKING:
@@ -296,7 +296,7 @@ class ToDocX(Tokenizer):
elif tType == BlockTyp.SKIP:
self._processFragments(par, S_NORM, "")
elif tType == BlockTyp.COMMENT:
elif tType in COMMENT_BLOCKS:
self._processFragments(par, S_META, tText, tFormat)
elif tType == BlockTyp.KEYWORD:
novelwriter/formats/tohtml.py
+47 -45
View File
@@ -32,7 +32,7 @@ from typing import TYPE_CHECKING
from novelwriter.common import formatTimeStamp
from novelwriter.constants import nwHtmlUnicode, nwStyles
from novelwriter.formats.shared import BlockFmt, BlockTyp, T_Formats, TextFmt, stripEscape
from novelwriter.formats.tokenizer import Tokenizer
from novelwriter.formats.tokenizer import COMMENT_BLOCKS, Tokenizer
from novelwriter.types import FONT_STYLE, FONT_WEIGHTS, QtHexRgb
if TYPE_CHECKING:
@@ -159,34 +159,33 @@ class ToHtml(Tokenizer):
# If we don't have formatting, we can do a plain replace
tText = tText.replace("<", "&lt;").replace(">", "&gt;")
# Styles
# Inline Styles
aStyle = []
if self._cssStyles:
if tStyle & BlockFmt.LEFT:
aStyle.append("text-align: left;")
elif tStyle & BlockFmt.RIGHT:
aStyle.append("text-align: right;")
elif tStyle & BlockFmt.CENTRE:
aStyle.append("text-align: center;")
elif tStyle & BlockFmt.JUSTIFY:
aStyle.append("text-align: justify;")
if tStyle & BlockFmt.LEFT:
aStyle.append("text-align: left;")
elif tStyle & BlockFmt.RIGHT:
aStyle.append("text-align: right;")
elif tStyle & BlockFmt.CENTRE:
aStyle.append("text-align: center;")
elif tStyle & BlockFmt.JUSTIFY:
aStyle.append("text-align: justify;")
if tStyle & BlockFmt.PBB:
aStyle.append("page-break-before: always;")
if tStyle & BlockFmt.PBA:
aStyle.append("page-break-after: always;")
if tStyle & BlockFmt.PBB:
aStyle.append("page-break-before: always;")
if tStyle & BlockFmt.PBA:
aStyle.append("page-break-after: always;")
if tStyle & BlockFmt.Z_BTM:
aStyle.append("margin-bottom: 0;")
if tStyle & BlockFmt.Z_TOP:
aStyle.append("margin-top: 0;")
if tStyle & BlockFmt.Z_BTM:
aStyle.append("margin-bottom: 0;")
if tStyle & BlockFmt.Z_TOP:
aStyle.append("margin-top: 0;")
if tStyle & BlockFmt.IND_L:
aStyle.append(f"margin-left: {self._blockIndent:.2f}em;")
if tStyle & BlockFmt.IND_R:
aStyle.append(f"margin-right: {self._blockIndent:.2f}em;")
if tStyle & BlockFmt.IND_T:
aStyle.append(f"text-indent: {self._firstWidth:.2f}em;")
if tStyle & BlockFmt.IND_L:
aStyle.append(f"margin-left: {self._blockIndent:.2f}em;")
if tStyle & BlockFmt.IND_R:
aStyle.append(f"margin-right: {self._blockIndent:.2f}em;")
if tStyle & BlockFmt.IND_T:
aStyle.append(f"text-indent: {self._firstWidth:.2f}em;")
if aStyle:
stVals = " ".join(aStyle)
@@ -229,7 +228,7 @@ class ToHtml(Tokenizer):
elif tType == BlockTyp.SKIP:
lines.append(f"<p{hStyle}>&nbsp;</p>\n")
elif tType == BlockTyp.COMMENT:
elif tType in COMMENT_BLOCKS:
lines.append(f"<p class='comment'{hStyle}>{self._formatText(tText, tFmt)}</p>\n")
elif tType == BlockTyp.KEYWORD:
@@ -288,26 +287,25 @@ class ToHtml(Tokenizer):
json.dump(data, fObj, indent=2)
else:
html = []
html.append("<!DOCTYPE html>")
html.append("<html>")
html.append("<head>")
html.append(f"<title>{self._project.data.name:s}</title>")
html.append("<meta charset='utf-8'>")
if self._cssStyles:
html.append("<meta name='viewport' content='width=device-width, initial-scale=1'>")
html.append("<style>")
html.extend(self.getStyleSheet())
html.append("</style>")
html.append("</head>")
html.append("<body>")
html.append(("".join(self._pages)).replace("\t", "&#09;").rstrip())
html.append("</body>")
html.append("</html>\n")
with open(path, mode="w", encoding="utf-8") as fObj:
fObj.write((
"<!DOCTYPE html>\n"
"<html>\n"
"<head>\n"
"<meta charset='utf-8'>\n"
"<title>{title:s}</title>\n"
"<style>\n"
"{style:s}\n"
"</style>\n"
"</head>\n"
"<body>\n"
"{body:s}\n"
"</body>\n"
"</html>\n"
).format(
title=self._project.data.name,
style="\n".join(self.getStyleSheet()),
body=("".join(self._pages)).replace("\t", "&#09;").rstrip(),
))
fObj.write("\n".join(html))
logger.info("Wrote file: %s", path)
@@ -410,7 +408,11 @@ class ToHtml(Tokenizer):
# isn't already open, and only closed if it has previously been opened.
tags: list[tuple[int, str]] = []
state = dict.fromkeys(HTML_OPENER, False)
plain = not self._cssStyles
for pos, fmt, data in tFmt:
if plain and fmt in (TextFmt.COL_B, TextFmt.COL_E):
# We ignore colour tags if CSS is off
continue
if m := HTML_OPENER.get(fmt):
if not state.get(fmt, True):
if fmt == TextFmt.COL_B and (color := self._classes.get(data)):
novelwriter/formats/tokenizer.py
+22 -9
View File
@@ -71,11 +71,23 @@ COMMENT_STYLE = {
nwComment.COMMENT: ComStyle(),
nwComment.STORY: ComStyle("Story Structure", "modifier", "note"),
}
HEADINGS = [
COMMENT_TYPE = {
nwComment.PLAIN: BlockTyp.COMMENT,
nwComment.IGNORE: BlockTyp.COMMENT,
nwComment.SYNOPSIS: BlockTyp.SUMMARY,
nwComment.SHORT: BlockTyp.SUMMARY,
nwComment.NOTE: BlockTyp.NOTE,
nwComment.FOOTNOTE: BlockTyp.COMMENT,
nwComment.COMMENT: BlockTyp.COMMENT,
nwComment.STORY: BlockTyp.NOTE,
}
HEADING_BLOCKS = [
BlockTyp.TITLE, BlockTyp.PART, BlockTyp.HEAD1,
BlockTyp.HEAD2, BlockTyp.HEAD3, BlockTyp.HEAD4,
]
SKIP_INDENT = [*HEADINGS, BlockTyp.SEP, BlockTyp.SKIP]
COMMENT_BLOCKS = (BlockTyp.COMMENT, BlockTyp.SUMMARY, BlockTyp.NOTE)
META_BLOCKS = (BlockTyp.COMMENT, BlockTyp.SUMMARY, BlockTyp.NOTE, BlockTyp.KEYWORD)
SKIP_INDENT = [*HEADING_BLOCKS, BlockTyp.SEP, BlockTyp.SKIP]
B_EMPTY: T_Block = (BlockTyp.EMPTY, "", "", [], BlockFmt.NONE)
@@ -189,6 +201,7 @@ class Tokenizer(ABC):
(REGEX_PATTERNS.markdownItalic, [0, TextFmt.I_B, 0, TextFmt.I_E]),
(REGEX_PATTERNS.markdownBold, [0, TextFmt.B_B, 0, TextFmt.B_E]),
(REGEX_PATTERNS.markdownStrike, [0, TextFmt.D_B, 0, TextFmt.D_E]),
(REGEX_PATTERNS.markdownMark, [0, TextFmt.M_B, 0, TextFmt.M_E]),
]
self._shortCodeFmt = {
@@ -618,7 +631,7 @@ class Tokenizer(ABC):
bStyle = COMMENT_STYLE[cStyle]
tLine, tFmt = self._formatComment(bStyle, cKey, cText)
tBlocks.append((
BlockTyp.COMMENT, "", tLine, tFmt, tStyle
COMMENT_TYPE[cStyle], "", tLine, tFmt, tStyle
))
elif cStyle == nwComment.FOOTNOTE:
@@ -862,12 +875,12 @@ class Tokenizer(ABC):
# We don't need to keep the empty lines after this pass
pass
elif cBlock[0] == BlockTyp.KEYWORD:
# Adjust margins for lines in a list of keyword lines
elif cBlock[0] in (BlockTyp.KEYWORD, BlockTyp.NOTE):
# Adjust margins for lines in repeated meta blocks
aStyle = cBlock[4]
if pBlock[0] == BlockTyp.KEYWORD:
if pBlock[0] == cBlock[0]:
aStyle |= BlockFmt.Z_TOP
if nBlock[0] == BlockTyp.KEYWORD:
if nBlock[0] == cBlock[0]:
aStyle |= BlockFmt.Z_BTM
sBlocks.append((
cBlock[0], cBlock[1], cBlock[2], cBlock[3], aStyle
@@ -991,7 +1004,7 @@ class Tokenizer(ABC):
allWordChars += nPWChars
textWordChars += nPWChars
elif tType in HEADINGS:
elif tType in HEADING_BLOCKS:
titleCount += 1
allWords += nWords
titleWords += nWords
@@ -1005,7 +1018,7 @@ class Tokenizer(ABC):
allChars += nChars
allWordChars += nWChars
elif tType in (BlockTyp.COMMENT, BlockTyp.KEYWORD):
elif tType in META_BLOCKS:
words = tText.split()
allWords += len(words)
allChars += len(tText)
novelwriter/formats/tomarkdown.py
+2 -2
View File
@@ -29,7 +29,7 @@ from typing import TYPE_CHECKING
from novelwriter.constants import nwUnicode
from novelwriter.formats.shared import BlockFmt, BlockTyp, T_Formats, TextFmt
from novelwriter.formats.tokenizer import Tokenizer
from novelwriter.formats.tokenizer import COMMENT_BLOCKS, Tokenizer
if TYPE_CHECKING:
from pathlib import Path
@@ -144,7 +144,7 @@ class ToMarkdown(Tokenizer):
elif tType == BlockTyp.SKIP:
lines.append(f"{cSkip}\n\n")
elif tType == BlockTyp.COMMENT:
elif tType in COMMENT_BLOCKS:
lines.append(f"{self._formatText(tText, tFormat, mTags)}\n\n")
elif tType == BlockTyp.KEYWORD:
novelwriter/formats/toodt.py
+2 -2
View File
@@ -40,7 +40,7 @@ from novelwriter import __version__
from novelwriter.common import xmlElement, xmlIndent, xmlSubElem
from novelwriter.constants import nwHeadFmt, nwStyles
from novelwriter.formats.shared import BlockFmt, BlockTyp, TextFmt, stripEscape
from novelwriter.formats.tokenizer import Tokenizer
from novelwriter.formats.tokenizer import COMMENT_BLOCKS, Tokenizer
from novelwriter.types import FONT_STYLE, QtHexRgb
if TYPE_CHECKING:
@@ -389,7 +389,7 @@ class ToOdt(Tokenizer):
elif tType == BlockTyp.SKIP:
self._addTextPar(xText, S_TEXT, oStyle, "")
elif tType == BlockTyp.COMMENT:
elif tType in COMMENT_BLOCKS:
self._addTextPar(xText, S_META, oStyle, tText, tFmt=tFormat)
elif tType == BlockTyp.KEYWORD:
novelwriter/formats/toqdoc.py
+8 -4
View File
@@ -37,7 +37,7 @@ from PyQt6.QtPrintSupport import QPrinter
from novelwriter import __version__
from novelwriter.constants import nwStyles, nwUnicode
from novelwriter.formats.shared import BlockFmt, BlockTyp, T_Formats, TextFmt, stripEscape
from novelwriter.formats.tokenizer import HEADINGS, Tokenizer
from novelwriter.formats.tokenizer import HEADING_BLOCKS, META_BLOCKS, Tokenizer
from novelwriter.types import (
QtAlignAbsolute, QtAlignCenter, QtAlignJustify, QtAlignLeft, QtAlignRight,
QtKeepAnchor, QtMoveAnchor, QtPageBreakAfter, QtPageBreakAuto,
@@ -214,7 +214,7 @@ class ToQTextDocument(Tokenizer):
for tType, tMeta, tText, tFormat, tStyle in self._blocks:
bFmt = QTextBlockFormat(self._blockFmt)
if tType in (BlockTyp.COMMENT, BlockTyp.KEYWORD):
if tType in META_BLOCKS:
bFmt.setTopMargin(self._mMeta[0])
bFmt.setBottomMargin(self._mMeta[1])
elif tType == BlockTyp.SEP:
@@ -248,17 +248,21 @@ class ToQTextDocument(Tokenizer):
if tStyle & BlockFmt.IND_T:
bFmt.setTextIndent(self._tIndent)
if tType in (BlockTyp.TEXT, BlockTyp.COMMENT, BlockTyp.KEYWORD):
if tType == BlockTyp.TEXT:
newBlock(cursor, bFmt)
self._insertFragments(tText, tFormat, cursor, self._charFmt)
elif tType in HEADINGS:
elif tType in HEADING_BLOCKS:
bFmt, cFmt = self._genHeadStyle(tType, tMeta, bFmt)
for tPart in tText.split("\n"):
newBlock(cursor, bFmt)
cursor.insertText(tPart, cFmt)
bFmt.setPageBreakPolicy(QtPageBreakAuto)
elif tType in META_BLOCKS:
newBlock(cursor, bFmt)
self._insertFragments(tText, tFormat, cursor, self._charFmt)
elif tType == BlockTyp.SEP:
newBlock(cursor, bFmt)
cursor.insertText(tText, self._charFmt)