novelWriter 2.3.1__py3-none-any.whl → 2.4__py3-none-any.whl

novelwriter/core/index.py

@@ -3,7 +3,6 @@ novelWriter – Project Index
 ===========================
 
 File History:
-Created: 2019-04-22 [0.0.1]  countWords
 Created: 2019-05-27 [0.1.4]  NWIndex
 Created: 2022-05-28 [2.0rc1] IndexItem
 Created: 2022-05-28 [2.0rc1] IndexHeading
@@ -34,13 +33,14 @@ import logging
 from time import time
 from typing import TYPE_CHECKING
 from pathlib import Path
-from collections.abc import ItemsView, Iterable, Iterator
+from collections.abc import ItemsView, Iterable
 
 from novelwriter import SHARED
 from novelwriter.enum import nwComment, nwItemClass, nwItemType, nwItemLayout
 from novelwriter.error import logException
 from novelwriter.common import checkInt, isHandle, isItemClass, isTitleTag, jsonEncode
-from novelwriter.constants import nwFiles, nwKeyWords, nwRegEx, nwUnicode, nwHeaders
+from novelwriter.constants import nwFiles, nwKeyWords, nwHeaders
+from novelwriter.text.counting import standardCounter
 
 if TYPE_CHECKING:  # pragma: no cover
     from novelwriter.core.item import NWItem
@@ -122,9 +122,8 @@ class NWIndex:
         self.clearIndex()
         for nwItem in self._project.tree:
             if nwItem.isFileType():
-                tHandle = nwItem.itemHandle
-                doc = self._project.storage.getDocument(tHandle)
-                self.scanText(tHandle, doc.readDocument() or "", blockSignal=True)
+                text = self._project.storage.getDocumentText(nwItem.itemHandle)
+                self.scanText(nwItem.itemHandle, text, blockSignal=True)
         self._indexBroken = False
         SHARED.indexSignalProxy({"event": "buildIndex"})
         return
@@ -142,17 +141,15 @@ class NWIndex:
         })
         return
 
-    def reIndexHandle(self, tHandle: str | None) -> bool:
+    def reIndexHandle(self, tHandle: str | None) -> None:
         """Put a file back into the index. This is used when files are
         moved from the archive or trash folders back into the active
         project.
         """
         if tHandle and self._project.tree.checkType(tHandle, nwItemType.FILE):
             logger.debug("Re-indexing item '%s'", tHandle)
-            doc = self._project.storage.getDocument(tHandle)
-            self.scanText(tHandle, doc.readDocument() or "")
-            return True
-        return False
+            self.scanText(tHandle, self._project.storage.getDocumentText(tHandle))
+        return
 
     def indexChangedSince(self, checkTime: int | float) -> bool:
         """Check if the index has changed since a given time."""
@@ -266,7 +263,7 @@ class NWIndex:
         self._itemIndex.add(tHandle, tItem)
 
         # Run word counter for the whole text
-        cC, wC, pC = countWords(text)
+        cC, wC, pC = standardCounter(text)
         tItem.setCharCount(cC)
         tItem.setWordCount(wC)
         tItem.setParaCount(pC)
@@ -307,7 +304,7 @@ class NWIndex:
         nTitle = 0           # Line Number of the previous title
         cTitle = TT_NONE     # Tag of the current title
         pTitle = TT_NONE     # Tag of the previous title
-        canSetHeader = True  # First header has not yet been set
+        canSetHead = True  # First heading has not yet been set
 
         lines = text.splitlines()
         for n, line in enumerate(lines, start=1):
@@ -320,9 +317,9 @@ class NWIndex:
                 if hDepth == "H0":
                     continue
 
-                if canSetHeader:
+                if canSetHead:
                     nwItem.setMainHeading(hDepth)
-                    canSetHeader = False
+                    canSetHead = False
 
                 cTitle = self._itemIndex.addItemHeading(tHandle, n, hDepth, hText)
                 if cTitle != TT_NONE:
@@ -383,7 +380,7 @@ class NWIndex:
         return
 
     def _splitHeading(self, line: str) -> tuple[str, str]:
-        """Split a heading into its header level and text value."""
+        """Split a heading into its heading level and text value."""
         if line.startswith("# "):
             return "H1", line[2:].strip()
         elif line.startswith("## "):
@@ -396,11 +393,13 @@ class NWIndex:
             return "H1", line[3:].strip()
         elif line.startswith("##! "):
             return "H2", line[4:].strip()
+        elif line.startswith("###! "):
+            return "H3", line[5:].strip()
         return "H0", ""
 
     def _indexWordCounts(self, tHandle: str, text: str, sTitle: str) -> None:
         """Count text stats and save the counts to the index."""
-        cC, wC, pC = countWords(text)
+        cC, wC, pC = standardCounter(text)
         self._itemIndex.setHeadingCounts(tHandle, sTitle, cC, wC, pC)
         return
 
@@ -515,16 +514,21 @@ class NWIndex:
         """Get the index data for a given item."""
         return self._itemIndex[tHandle]
 
-    def getItemHeader(self, tHandle: str, sTitle: str) -> IndexHeading | None:
-        """Get the header entry for a specific item and heading."""
-        tItem = self._itemIndex[tHandle]
-        if isinstance(tItem, IndexItem):
+    def getItemHeading(self, tHandle: str, sTitle: str) -> IndexHeading | None:
+        """Get the heading entry for a specific item and heading."""
+        if tItem := self._itemIndex[tHandle]:
             return tItem[sTitle]
         return None
 
+    def iterItemHeadings(self, tHandle: str) -> Iterable[tuple[str, IndexHeading]]:
+        """Get all headings for a specific item."""
+        if tItem := self._itemIndex[tHandle]:
+            yield from tItem.items()
+        return []
+
     def novelStructure(
         self, rootHandle: str | None = None, activeOnly: bool = True
-    ) -> Iterator[tuple[str, str, str, IndexHeading]]:
+    ) -> Iterable[tuple[str, str, str, IndexHeading]]:
         """Iterate over all titles in the novel, in the correct order as
         they appear in the tree view and in the respective document
         files, but skipping all note files.
@@ -666,7 +670,7 @@ class NWIndex:
 
     def getTagsData(
         self, activeOnly: bool = True
-    ) -> Iterator[tuple[str, str, str, IndexItem | None, IndexHeading | None]]:
+    ) -> Iterable[tuple[str, str, str, IndexItem | None, IndexHeading | None]]:
         """Return all known tags."""
         for tag, data in self._tagsIndex.items():
             iItem = self._itemIndex[data.get("handle")]
@@ -825,7 +829,7 @@ class ItemIndex:
     class around a single storage dictionary with a set of utility
     functions for setting and accessing the index data. Each indexed
     item is stored in an IndexItem object, which again holds an
-    IndexHeading object for each header of the text.
+    IndexHeading object for each heading of the text.
     """
 
     __slots__ = ("_project", "_items")
@@ -898,13 +902,11 @@ class ItemIndex:
 
             if rHandle is None:
                 for sTitle in self._items[tHandle].headings():
-                    hItem = self._items[tHandle][sTitle]
-                    if hItem:
+                    if hItem := self._items[tHandle][sTitle]:
                         yield tHandle, sTitle, hItem
             elif tItem.itemRoot == rHandle:
                 for sTitle in self._items[tHandle].headings():
-                    hItem = self._items[tHandle][sTitle]
-                    if hItem:
+                    if hItem := self._items[tHandle][sTitle]:
                         yield tHandle, sTitle, hItem
 
         return
@@ -1200,7 +1202,7 @@ class IndexHeading:
     ##
 
     def setLevel(self, level: str) -> None:
-        """Set the level of the header if it's a valid value."""
+        """Set the level of the heading if it's a valid value."""
         if level in nwHeaders.H_VALID:
             self._level = level
         return
@@ -1315,86 +1317,3 @@ def processComment(text: str) -> tuple[nwComment, str, int]:
     if content and (clean := classifier.strip().lower()) in CLASSIFIERS:
         return CLASSIFIERS[clean], content.strip(), text.find(":") + 1
     return nwComment.PLAIN, check, 0
-
-
-def countWords(text: str) -> tuple[int, int, int]:
-    """Count words in a piece of text, skipping special syntax and
-    comments.
-    """
-    charCount = 0
-    wordCount = 0
-    paraCount = 0
-    prevEmpty = True
-
-    if not isinstance(text, str):
-        return charCount, wordCount, paraCount
-
-    # We need to treat dashes as word separators for counting words.
-    # The check+replace approach is much faster than direct replace for
-    # large texts, and a bit slower for small texts, but in the latter
-    # case it doesn't really matter.
-    if nwUnicode.U_ENDASH in text:
-        text = text.replace(nwUnicode.U_ENDASH, " ")
-    if nwUnicode.U_EMDASH in text:
-        text = text.replace(nwUnicode.U_EMDASH, " ")
-
-    # Strip shortcodes
-    if "[" in text:
-        text = nwRegEx.RX_SC.sub("", text)
-
-    for line in text.splitlines():
-
-        countPara = True
-
-        if not line:
-            prevEmpty = True
-            continue
-
-        if line[0] == "@" or line[0] == "%":
-            continue
-
-        if line[0] == "[":
-            check = line.lower()
-            if check.startswith(("[newpage]", "[new page]", "[vspace]")):
-                continue
-            elif check.startswith("[vspace:") and line.endswith("]"):
-                continue
-
-        elif line[0] == "#":
-            if line[:5] == "#### ":
-                line = line[5:]
-                countPara = False
-            elif line[:4] == "### ":
-                line = line[4:]
-                countPara = False
-            elif line[:3] == "## ":
-                line = line[3:]
-                countPara = False
-            elif line[:2] == "# ":
-                line = line[2:]
-                countPara = False
-            elif line[:3] == "#! ":
-                line = line[3:]
-                countPara = False
-            elif line[:4] == "##! ":
-                line = line[4:]
-                countPara = False
-
-        elif line[0] == ">" or line[-1] == "<":
-            if line[:2] == ">>":
-                line = line[2:].lstrip(" ")
-            elif line[:1] == ">":
-                line = line[1:].lstrip(" ")
-            if line[-2:] == "<<":
-                line = line[:-2].rstrip(" ")
-            elif line[-1:] == "<":
-                line = line[:-1].rstrip(" ")
-
-        wordCount += len(line.split())
-        charCount += len(line)
-        if countPara and prevEmpty:
-            paraCount += 1
-
-        prevEmpty = not countPara
-
-    return charCount, wordCount, paraCount

novelwriter/core/project.py

@@ -31,7 +31,7 @@ from time import time
 from typing import TYPE_CHECKING
 from pathlib import Path
 from functools import partial
-from collections.abc import Iterator
+from collections.abc import Iterable
 
 from PyQt5.QtCore import QCoreApplication
 
@@ -175,12 +175,10 @@ class NWProject:
         """Write content to a new document after it is created. This
         will not run if the file exists and is not empty.
         """
-        tItem = self._tree[tHandle]
-        if not (tItem and tItem.isFileType()):
+        if not ((tItem := self._tree[tHandle]) and tItem.isFileType()):
             return False
 
-        newDoc = self._storage.getDocument(tHandle)
-        if (newDoc.readDocument() or "").strip():
+        if self._storage.getDocumentText(tHandle).strip():
             return False
 
         indent = "#"*minmax(hLevel, 1, 4)
@@ -191,7 +189,7 @@ class NWProject:
         else:
             tItem.setLayout(nwItemLayout.NOTE)
 
-        newDoc.writeDocument(text)
+        self._storage.getDocument(tHandle).writeDocument(text)
         self._index.scanText(tHandle, text)
 
         return True
@@ -200,21 +198,18 @@ class NWProject:
         """Copy content to a new document after it is created. This
         will not run if the file exists and is not empty.
         """
-        tItem = self._tree[tHandle]
-        if not (tItem and tItem.isFileType()):
+        if not ((tItem := self._tree[tHandle]) and tItem.isFileType()):
             return False
 
-        sItem = self._tree[sHandle]
-        if not (sItem and sItem.isFileType()):
+        if not ((sItem := self._tree[sHandle]) and sItem.isFileType()):
             return False
 
-        newDoc = self._storage.getDocument(tHandle)
-        if (newDoc.readDocument() or "").strip():
+        if self._storage.getDocumentText(tHandle).strip():
             return False
 
         logger.debug("Populating '%s' with text from '%s'", tHandle, sHandle)
-        text = self._storage.getDocument(sHandle).readDocument() or ""
-        newDoc.writeDocument(text)
+        text = self._storage.getDocumentText(sHandle)
+        self._storage.getDocument(tHandle).writeDocument(text)
         sItem.setLayout(tItem.itemLayout)
         self._index.scanText(tHandle, text)
 
@@ -517,7 +512,7 @@ class NWProject:
     #  Class Methods
     ##
 
-    def iterProjectItems(self) -> Iterator[NWItem]:
+    def iterProjectItems(self) -> Iterable[NWItem]:
         """This function ensures that the item tree loaded is sent to
         the GUI tree view in such a way that the tree can be built. That
         is, the parent item must be sent before its child. In principle,

novelwriter/core/projectxml.py

@@ -449,7 +449,7 @@ class ProjectXMLReader:
                 result[xEntry.attrib["key"]] = checkString(xEntry.text, "")
         return result
 
-    def _parseDictTagText(self, xItem) -> dict:
+    def _parseDictTagText(self, xItem: ET.Element) -> dict:
         """Parse a dictionary stored with key as the tag and the value
         as the text property.
         """

novelwriter/core/sessions.py

@@ -29,7 +29,7 @@ import logging
 from time import time
 from typing import TYPE_CHECKING
 from pathlib import Path
-from collections.abc import Iterator
+from collections.abc import Iterable
 
 from novelwriter.error import logException
 from novelwriter.common import formatTimeStamp
@@ -110,7 +110,7 @@ class NWSessionLog:
 
         return True
 
-    def iterRecords(self) -> Iterator[dict]:
+    def iterRecords(self) -> Iterable[dict]:
         """Iterate through all records in the log."""
         sessFile = self._project.storage.getMetaFile(nwFiles.SESS_FILE)
         if isinstance(sessFile, Path) and sessFile.is_file():

novelwriter/core/spellcheck.py

@@ -74,7 +74,7 @@ class NWSpellEnchant:
     #  Setters
     ##
 
-    def setLanguage(self, language: str | None):
+    def setLanguage(self, language: str | None) -> None:
         """Load a dictionary for the language specified in the config.
         If that fails, we load a mock dictionary so that lookups don't
         crash. Note that enchant will allow loading an empty string as
@@ -182,10 +182,10 @@ class FakeEnchant:
     def check(self, word: str) -> bool:
         return True
 
-    def suggest(self, word) -> list[str]:
+    def suggest(self, word: str) -> list[str]:
         return []
 
-    def add_to_session(self, word: str):
+    def add_to_session(self, word: str) -> None:
         return
 
 # END Class FakeEnchant

novelwriter/core/status.py

@@ -28,13 +28,14 @@ import random
 import logging
 
 from typing import TYPE_CHECKING, Literal
-from collections.abc import ItemsView, Iterator, KeysView, ValuesView
+from collections.abc import ItemsView, Iterable, Iterator, KeysView, ValuesView
 
 from PyQt5.QtGui import QIcon, QPainter, QPainterPath, QPixmap, QColor
-from PyQt5.QtCore import QRectF, Qt
+from PyQt5.QtCore import QRectF
 
 from novelwriter import CONFIG
 from novelwriter.common import minmax, simplified
+from novelwriter.types import QtPaintAnitAlias, QtTransparent
 
 if TYPE_CHECKING:  # pragma: no cover
     from typing import TypeGuard  # Requires Python 3.10
@@ -193,7 +194,7 @@ class NWStatus:
             self._store[key]["count"] += 1
         return
 
-    def pack(self) -> Iterator[tuple[str, dict]]:
+    def pack(self) -> Iterable[tuple[str, dict]]:
         """Pack the status entries into a dictionary."""
         for key, data in self._store.items():
             yield (data["name"], {
@@ -248,10 +249,10 @@ class NWStatus:
     def _createIcon(self, red: int, green: int, blue: int) -> QIcon:
         """Generate an icon for a status label."""
         pixmap = QPixmap(self._iPX, self._iPX)
-        pixmap.fill(Qt.transparent)
+        pixmap.fill(QtTransparent)
 
         painter = QPainter(pixmap)
-        painter.setRenderHint(QPainter.Antialiasing)
+        painter.setRenderHint(QtPaintAnitAlias)
         painter.fillPath(self._iconPath, QColor(red, green, blue))
         painter.end()
 

novelwriter/core/storage.py

@@ -27,18 +27,18 @@ import json
 import logging
 
 from enum import Enum
+from pathlib import Path
 from time import time
 from typing import TYPE_CHECKING
-from pathlib import Path
 from zipfile import ZIP_DEFLATED, ZIP_STORED, ZipFile
 
 from novelwriter import CONFIG
-from novelwriter.error import logException
 from novelwriter.common import isHandle, minmax
 from novelwriter.constants import nwFiles
 from novelwriter.core.document import NWDocument
 from novelwriter.core.projectxml import ProjectXMLReader, ProjectXMLWriter
 from novelwriter.core.spellcheck import UserDictionary
+from novelwriter.error import logException
 
 if TYPE_CHECKING:  # pragma: no cover
     from novelwriter.core.project import NWProject
@@ -287,6 +287,12 @@ class NWStorage:
             return self._runtimePath / "meta" / fileName
         return None
 
+    def getDocumentText(self, tHandle: str) -> str:
+        """Return the text of a document in a fast and efficient way."""
+        if isinstance(self._runtimePath, Path):
+            return NWDocument.quickReadText(self._runtimePath / "content", tHandle)
+        return ""
+
     def scanContent(self) -> list[str]:
         """Scan the content folder and return the handle of all files
         found in it. Files that do not match the pattern are ignored.

novelwriter/core/tohtml.py

@@ -74,15 +74,9 @@ class ToHtml(Tokenizer):
     #  Setters
     ##
 
-    def setPreview(self, doComments: bool, doSynopsis: bool) -> None:
-        """If we're using this class to generate markdown preview, we
-        need to make a few changes to formatting, which is managed by
-        these flags.
-        """
-        self._genMode = self.M_PREVIEW
-        self._doKeywords = True
-        self._doComments = doComments
-        self._doSynopsis = doSynopsis
+    def setPreview(self, state: bool) -> None:
+        """Set to preview generator mode."""
+        self._genMode = self.M_PREVIEW if state else self.M_EXPORT
         return
 
     def setStyles(self, cssStyles: bool) -> None:
@@ -133,6 +127,8 @@ class ToHtml(Tokenizer):
                 self.FMT_D_E: "</span>",
                 self.FMT_U_B: "<u>",
                 self.FMT_U_E: "</u>",
+                self.FMT_M_B: "<mark>",
+                self.FMT_M_E: "</mark>",
             }
         else:
             htmlTags = {  # HTML5 (for export)
@@ -144,6 +140,8 @@ class ToHtml(Tokenizer):
                 self.FMT_D_E: "</del>",
                 self.FMT_U_B: "<span style='text-decoration: underline;'>",
                 self.FMT_U_E: "</span>",
+                self.FMT_M_B: "<mark>",
+                self.FMT_M_E: "</mark>",
             }
 
         htmlTags[self.FMT_SUP_B] = "<sup>"
@@ -171,6 +169,8 @@ class ToHtml(Tokenizer):
         pStyle = None
         lines = []
 
+        tHandle = self._handle
+
         for tType, nHead, tText, tFormat, tStyle in self._tokens:
 
             # Replace < and > with HTML entities
@@ -229,8 +229,8 @@ class ToHtml(Tokenizer):
             else:
                 hStyle = ""
 
-            if self._linkHeaders:
-                aNm = f"<a name='T{nHead:04d}'></a>"
+            if self._linkHeadings and tHandle:
+                aNm = f"<a name='{tHandle}:T{nHead:04d}'></a>"
             else:
                 aNm = ""
 
@@ -252,10 +252,6 @@ class ToHtml(Tokenizer):
                 tHead = tText.replace(nwHeadFmt.BR, "<br/>")
                 lines.append(f"<h1 class='title'{hStyle}>{aNm}{tHead}</h1>\n")
 
-            elif tType == self.T_UNNUM:
-                tHead = tText.replace(nwHeadFmt.BR, "<br/>")
-                lines.append(f"<{h2}{hStyle}>{aNm}{tHead}</{h2}>\n")
-
             elif tType == self.T_HEAD1:
                 tHead = tText.replace(nwHeadFmt.BR, "<br/>")
                 lines.append(f"<{h1}{h1Cl}{hStyle}>{aNm}{tHead}</{h1}>\n")
@@ -296,12 +292,13 @@ class ToHtml(Tokenizer):
                 lines.append(self._formatComments(tText))
 
             elif tType == self.T_KEYWORD and self._doKeywords:
-                tTemp = f"<p{hStyle}>{self._formatKeywords(tText)}</p>\n"
+                tag, text = self._formatKeywords(tText)
+                kClass = f" class='meta meta-{tag}'" if tag else ""
+                tTemp = f"<p{kClass}{hStyle}>{text}</p>\n"
                 lines.append(tTemp)
 
         self._result = "".join(lines)
-        if self._genMode != self.M_PREVIEW:
-            self._fullHTML.append(self._result)
+        self._fullHTML.append(self._result)
 
         return
 
@@ -364,13 +361,12 @@ class ToHtml(Tokenizer):
 
     def getStyleSheet(self) -> list[str]:
         """Generate a stylesheet for the current settings."""
-        styles = []
         if not self._cssStyles:
-            return styles
+            return []
 
         mScale = self._lineHeight/1.15
-        textAlign = "justify" if self._doJustify else "left"
 
+        styles = []
         styles.append("body {{font-family: '{0:s}'; font-size: {1:d}pt;}}".format(
             self._textFont, self._textSize
         ))
@@ -380,7 +376,7 @@ class ToHtml(Tokenizer):
             "margin-top: {2:.2f}em; margin-bottom: {3:.2f}em;"
             "}}"
         ).format(
-            textAlign,
+            "justify" if self._doJustify else "left",
             round(100 * self._lineHeight),
             mScale * self._marginText[0],
             mScale * self._marginText[1],
@@ -445,6 +441,7 @@ class ToHtml(Tokenizer):
         ))
 
         styles.append("a {color: rgb(66, 113, 174);}")
+        styles.append("mark {background: rgb(255, 255, 166);}")
         styles.append(".tags {color: rgb(245, 135, 31); font-weight: bold;}")
         styles.append(".break {text-align: left;}")
         styles.append(".synopsis {font-style: italic;}")
@@ -475,11 +472,11 @@ class ToHtml(Tokenizer):
             sComm = self._localLookup("Comment")
             return f"<p class='comment'><strong>{sComm}:</strong> {text}</p>\n"
 
-    def _formatKeywords(self, text: str) -> str:
+    def _formatKeywords(self, text: str) -> tuple[str, str]:
         """Apply HTML formatting to keywords."""
         valid, bits, _ = self._project.index.scanThis("@"+text)
         if not valid or not bits or bits[0] not in nwLabels.KEY_NAME:
-            return ""
+            return "", ""
 
         result = f"<span class='tags'>{self._localLookup(nwLabels.KEY_NAME[bits[0]])}:</span> "
         if len(bits) > 1:
@@ -494,6 +491,6 @@ class ToHtml(Tokenizer):
                 else:
                     result += ", ".join(f"<a href='#tag_{t}'>{t}</a>" for t in bits[1:])
 
-        return result
+        return bits[0][1:], result
 
 # END Class ToHtml