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

Simplify JSON and raw text writing

Browse Source
This commit is contained in:
Veronica Berglyd Olsen
2024-10-15 23:59:25 +02:00
parent 34696ba3a8
commit c633a56bfb
13 changed files with 178 additions and 145 deletions
Download Patch File Download Diff File Expand all files Collapse all files
novelwriter/formats/tohtml.py
+2 -2
View File
@@ -290,9 +290,9 @@ class ToHtml(Tokenizer):
return
def saveDocument(self, path: str | Path, asJson: bool = False) -> None:
def saveDocument(self, path: Path) -> None:
"""Save the data to an HTML file."""
if asJson:
if path.suffix.lower() == ".json":
ts = time()
data = {
"meta": {
novelwriter/formats/tokenizer.py
+18 -61
View File
@@ -134,10 +134,10 @@ class Tokenizer(ABC):
self._project = project
# Data Variables
self._text = "" # The raw text to be tokenized
self._handle = None # The item handle currently being processed
self._result = "" # The result of the last document
self._keepMD = False # Whether to keep the markdown text
self._text = "" # The raw text to be tokenized
self._handle = None # The item handle currently being processed
self._result = "" # The result of the last document
self._keepRaw = False # Whether to keep the raw text, used by ToRaw
# Tokens and Meta Data (Per Document)
self._tokens: list[T_Token] = []
@@ -473,11 +473,6 @@ class Tokenizer(ABC):
self._keepBreaks = state
return
def setKeepMarkdown(self, state: bool) -> None:
"""Keep original markdown during build."""
self._keepMD = state
return
##
# Class Methods
##
@@ -487,7 +482,7 @@ class Tokenizer(ABC):
raise NotImplementedError
@abstractmethod
def saveDocument(self, path: str | Path) -> None:
def saveDocument(self, path: Path) -> None:
raise NotImplementedError
def addRootHeading(self, tHandle: str) -> None:
@@ -509,7 +504,7 @@ class Tokenizer(ABC):
self._tokens.append((
self.T_TITLE, 1, title, [], textAlign
))
if self._keepMD:
if self._keepRaw:
self._markdown.append(f"#! {title}\n\n")
return
@@ -574,7 +569,7 @@ class Tokenizer(ABC):
tokens.append((
self.T_EMPTY, nHead, "", [], self.A_NONE
))
if self._keepMD:
if self._keepRaw:
tmpMarkdown.append("\n")
continue
@@ -632,26 +627,26 @@ class Tokenizer(ABC):
tokens.append((
self.T_SYNOPSIS, nHead, tLine, tFmt, sAlign
))
if self._doSynopsis and self._keepMD:
if self._doSynopsis and self._keepRaw:
tmpMarkdown.append(f"{aLine}\n")
elif cStyle == nwComment.SHORT:
tLine, tFmt = self._extractFormats(cText)
tokens.append((
self.T_SHORT, nHead, tLine, tFmt, sAlign
))
if self._doSynopsis and self._keepMD:
if self._doSynopsis and self._keepRaw:
tmpMarkdown.append(f"{aLine}\n")
elif cStyle == nwComment.FOOTNOTE:
tLine, tFmt = self._extractFormats(cText, skip=self.FMT_FNOTE)
self._footnotes[f"{tHandle}:{cKey}"] = (tLine, tFmt)
if self._keepMD:
if self._keepRaw:
tmpMarkdown.append(f"{aLine}\n")
else:
tLine, tFmt = self._extractFormats(cText)
tokens.append((
self.T_COMMENT, nHead, tLine, tFmt, sAlign
))
if self._doComments and self._keepMD:
if self._doComments and self._keepRaw:
tmpMarkdown.append(f"{aLine}\n")
elif aLine.startswith("@"):
@@ -668,7 +663,7 @@ class Tokenizer(ABC):
tokens.append((
self.T_KEYWORD, nHead, aLine[1:].strip(), [], sAlign
))
if self._doKeywords and self._keepMD:
if self._doKeywords and self._keepRaw:
tmpMarkdown.append(f"{aLine}\n")
elif aLine.startswith(("# ", "#! ")):
@@ -704,7 +699,7 @@ class Tokenizer(ABC):
tokens.append((
tType, nHead, tText, [], tStyle
))
if self._keepMD:
if self._keepRaw:
tmpMarkdown.append(f"{aLine}\n")
elif aLine.startswith(("## ", "##! ")):
@@ -739,7 +734,7 @@ class Tokenizer(ABC):
tokens.append((
tType, nHead, tText, [], tStyle
))
if self._keepMD:
if self._keepRaw:
tmpMarkdown.append(f"{aLine}\n")
elif aLine.startswith(("### ", "###! ")):
@@ -780,7 +775,7 @@ class Tokenizer(ABC):
tokens.append((
tType, nHead, tText, [], tStyle
))
if self._keepMD:
if self._keepRaw:
tmpMarkdown.append(f"{aLine}\n")
elif aLine.startswith("#### "):
@@ -810,7 +805,7 @@ class Tokenizer(ABC):
tokens.append((
tType, nHead, tText, [], tStyle
))
if self._keepMD:
if self._keepRaw:
tmpMarkdown.append(f"{aLine}\n")
else:
@@ -858,7 +853,7 @@ class Tokenizer(ABC):
tokens.append((
self.T_TEXT, nHead, tLine, tFmt, sAlign
))
if self._keepMD:
if self._keepRaw:
tmpMarkdown.append(f"{aLine}\n")
# If we have content, turn off the first page flag
@@ -877,7 +872,7 @@ class Tokenizer(ABC):
tokens.append((
self.T_EMPTY, nHead, "", [], self.A_NONE
))
if self._keepMD:
if self._keepRaw:
tmpMarkdown.append("\n")
self._markdown.append("".join(tmpMarkdown))
@@ -1245,41 +1240,3 @@ class HeadingFormatter:
hFormat = hFormat.replace(nwHeadFmt.CHAR_FOCUS, fText)
return hFormat
class ToRaw(Tokenizer):
def __init__(self, project: NWProject) -> None:
super().__init__(project)
self._keepMD = True
return
def doConvert(self) -> None:
return
def saveDocument(self, path: str | Path, asJson: bool = False) -> None:
"""Save the raw text to a plain text file."""
if asJson:
ts = time()
data = {
"meta": {
"projectName": self._project.data.name,
"novelAuthor": self._project.data.author,
"buildTime": int(ts),
"buildTimeStr": formatTimeStamp(ts),
},
"text": {
"nwd": [page.rstrip("\n").split("\n") for page in self._markdown],
}
}
with open(path, mode="w", encoding="utf-8") as fObj:
json.dump(data, fObj, indent=2)
else:
with open(path, mode="w", encoding="utf-8") as outFile:
for nwdPage in self._markdown:
outFile.write(nwdPage)
logger.info("Wrote file: %s", path)
return
novelwriter/formats/tomarkdown.py
+1 -3
View File
@@ -199,7 +199,7 @@ class ToMarkdown(Tokenizer):
return
def saveDocument(self, path: str | Path) -> None:
def saveDocument(self, path: Path) -> None:
"""Save the data to a plain text file."""
with open(path, mode="w", encoding="utf-8") as outFile:
outFile.write("".join(self._fullMD))
@@ -210,8 +210,6 @@ class ToMarkdown(Tokenizer):
"""Replace tabs with spaces."""
spaces = spaceChar*nSpaces
self._fullMD = [p.replace("\t", spaces) for p in self._fullMD]
if self._keepMD:
self._markdown = [p.replace("\t", spaces) for p in self._markdown]
return
##
novelwriter/formats/toodt.py
+1 -1
View File
@@ -543,7 +543,7 @@ class ToOdt(Tokenizer):
self._xText.insert(0, xFields)
return
def saveDocument(self, path: str | Path) -> None:
def saveDocument(self, path: Path) -> None:
"""Save the data to an .fodt or .odt file."""
if self._isFlat:
with open(path, mode="wb") as fObj:
novelwriter/formats/toqdoc.py
+1 -1
View File
@@ -275,7 +275,7 @@ class ToQTextDocument(Tokenizer):
return
def saveDocument(self, path: str | Path) -> None:
def saveDocument(self, path: Path) -> None:
"""Not implemented."""
return
novelwriter/formats/toraw.py
+86
View File
@@ -0,0 +1,86 @@
"""
novelWriter – Raw NW Text Format
================================
File History:
Created: 2024-10-15 [2.6b1] ToRaw
This file is a part of novelWriter
Copyright 2018–2024, Veronica Berglyd Olsen
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
"""
from __future__ import annotations
import json
import logging
from pathlib import Path
from time import time
from novelwriter.common import formatTimeStamp
from novelwriter.core.project import NWProject
from novelwriter.formats.tokenizer import Tokenizer
logger = logging.getLogger(__name__)
class ToRaw(Tokenizer):
"""Core: Raw novelWriter Text Writer
A class that will collect the minimally altered original source text
and write it to either a text or JSON file.
"""
def __init__(self, project: NWProject) -> None:
super().__init__(project)
self._keepRaw = True
return
def doConvert(self) -> None:
"""No conversion to perform."""
return
def saveDocument(self, path: Path) -> None:
"""Save the raw text to a plain text file."""
if path.suffix.lower() == ".json":
ts = time()
data = {
"meta": {
"projectName": self._project.data.name,
"novelAuthor": self._project.data.author,
"buildTime": int(ts),
"buildTimeStr": formatTimeStamp(ts),
},
"text": {
"nwd": [page.rstrip("\n").split("\n") for page in self._markdown],
}
}
with open(path, mode="w", encoding="utf-8") as fObj:
json.dump(data, fObj, indent=2)
else:
with open(path, mode="w", encoding="utf-8") as outFile:
for nwdPage in self._markdown:
outFile.write(nwdPage)
logger.info("Wrote file: %s", path)
return
def replaceTabs(self, nSpaces: int = 8, spaceChar: str = " ") -> None:
"""Replace tabs with spaces."""
spaces = spaceChar*nSpaces
self._markdown = [p.replace("\t", spaces) for p in self._markdown]
return