Add text stats to manuscript tool (#1717)

.gitignore

@@ -50,3 +50,6 @@ ToC.txt
 # Coverage
 /.coverage
 /coverage.*
+
+# Other
+/test.py

docs/source/index.rst

@@ -66,7 +66,6 @@ with pip. See :ref:`a_started` for more details.
    usage_format
    usage_shortcuts
    usage_typography
-   usage_projectformat
 
 .. toctree::
    :maxdepth: 1
@@ -80,7 +79,15 @@ with pip. See :ref:`a_started` for more details.
 
 .. toctree::
    :maxdepth: 1
-   :caption: Additional Topics
+   :caption: Additional Details
+   :hidden:
+
+   more_projectformat
+   more_counting
+
+.. toctree::
+   :maxdepth: 1
+   :caption: Technical Topics
    :hidden:
 
    tech_locations

docs/source/more_counting.rst

@@ -0,0 +1,98 @@
+.. _a_counting:
+
+********************
+Word and Text Counts
+********************
+
+This is an overview of how words and other counts of your text are performed. The counting rules
+should be relatively standard, and are compared to LibreOffice Writer rules.
+
+The counts provided in the app on the raw text is meant to be approximate. For more accurate
+counts, you need to build your manuscript in the :guilabel:`Manuscript Tool` and check the counts
+on the generated preview.
+
+
+Text Word Counts and Stats
+==========================
+
+These are the rules for the main counts available for for each document in a project.
+
+For all counts, the following rules apply.
+
+#. Short (–) and long (—) dashes are considered word separators.
+#. Any line starting with ``%`` or ``@`` is ignored.
+#. Trailing white spaces are ignored, including line breaks.
+#. Leading ``>`` and trailing ``<`` are ignored with any spaces next to them.
+#. Valid shortcodes and other commands wrapped in brackets ``[]`` are ignored.
+#. In-line Markdown syntax in text paragraphs is treated as part of the text.
+
+After the above preparation of the text, the following counts are available.
+
+**Character Count**
+   The character count is the sum of characters per line, including leading and in-text white space
+   characters, but excluding trailing white space characters. Shortcodes in the text are not
+   included, but Markdown codes are. Only headers and text are counted.
+
+**Word Count**
+   The words count is the sum of blocks of continuous character per line separated by any number of
+   white space characters or dashes. Only headers and text are counted.
+
+**Paragraph Count**
+   The paragraph count is the number of text blocks separated by one or more empty line. A line
+   consisting only of white spaces is considered empty.
+
+
+Manuscript Counts
+=================
+
+These are the rules for the counts available for a manuscript in the :guilabel:`Manuscript Tool`.
+The rules have been tuned to agree with LibreOffice Writer, but will vary slightly depending on the
+content of your text. LibreOffice Writer also counts the text in the page header, which the
+Manuscript Tool does not.
+
+The content of each line is counted after all formatting has been processed, so the result will be
+more accurate than the counts for text documents elsewhere in the app. The following rules apply:
+
+#. Short (–) and long (—) dashes are considered word separators.
+#. Leading and trailing white spaces are generally included, but paragraph breaks are not.
+#. Hard line breaks within paragraph are considered white space characters.
+#. All formatting codes are ignored, including shortcodes, commands and Markdown.
+#. Scene and section separators are counted.
+#. Comments and meta data lines are counted after they are formatted.
+#. Headers are counted after they are formatted with custom formats.
+
+The following counts are available:
+
+**Header Count**
+   The number of headers in the manuscript.
+
+**Paragraph Count**
+   The number of body text paragraphs in the manuscript.
+
+**Total Word Count**
+   The number of words in the manuscript, including any comments and meta data text.
+
+**Text Word Count**
+   The number of words in body text paragraphs, excluding all other text.
+
+**Header Word Count**
+   The number of words in headers, including inserted formatting like chapter numbers, etc.
+
+**Total Character Count**
+   The number of characters on all lines, including any comments and meta data text. Paragraph
+   breaks are not counted, but in-paragraph hard line breaks are.
+
+**Text Character Count**
+   The number of characters in body text paragraphs. Paragraph breaks are not counted, but
+   in-paragraph hard line breaks are.
+
+**Header Character Count**
+   The number of characters in headings.
+
+**Text Words Character Count**
+   The number of characters in body text paragraphs considered part of a word or punctuation. That
+   is, white space characters are not counted.
+
+**Header Words Character Count**
+   The number of characters in headers considered part of a word or punctuation. That is, white
+   space characters are not counted.

novelwriter/assets/icons/typicons_dark/icons.conf

@@ -100,6 +100,8 @@ status_time     = typ_stopwatch-grey.svg
 sticky-off      = typ_pin-outline.svg
 sticky-on       = typ_pin.svg
 unchecked       = mixed_input-unchecked.svg
+unfold-hide     = typ_arrow-right.svg
+unfold-show     = typ_arrow-down.svg
 up              = typ_chevron-up.svg
 view            = typ_eye.svg
 view_build      = typ_export-grey.svg

novelwriter/assets/icons/typicons_dark/typ_arrow-down.svg

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg width="24" height="24" version="1.2" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
+ <path d="m1.5077 8.1077 10.492 10.662 10.492-10.662c0.33846-0.33846 0.50769-0.84615 0.50769-1.1846 0-0.33846-0.16923-0.84615-0.50769-1.1846-0.33846-0.33846-0.67692-0.50769-1.1846-0.50769h-18.615c-0.50769 0-0.84615 0.16923-1.1846 0.50769-0.33846 0.33846-0.50769 0.84615-0.50769 1.1846 0 0.33846 0.16923 0.84615 0.50769 1.1846z" fill="#aeaeae" stroke-width="1.6923"/>
+</svg>

novelwriter/assets/icons/typicons_dark/typ_arrow-right.svg

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg width="24" height="24" version="1.2" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
+ <path d="m8.1077 22.492 10.662-10.492-10.662-10.492c-0.33846-0.33846-0.84615-0.50769-1.1846-0.50769-0.33846 0-0.84615 0.16923-1.1846 0.50769-0.33846 0.33846-0.50769 0.67692-0.50769 1.1846v18.615c0 0.50769 0.16923 0.84615 0.50769 1.1846 0.33846 0.33846 0.84615 0.50769 1.1846 0.50769 0.33846 0 0.84615-0.16923 1.1846-0.50769z" fill="#aeaeae" stroke-width="1.6923"/>
+</svg>

novelwriter/assets/icons/typicons_light/icons.conf

@@ -100,6 +100,8 @@ status_time     = typ_stopwatch-grey.svg
 sticky-off      = typ_pin-outline.svg
 sticky-on       = typ_pin.svg
 unchecked       = mixed_input-unchecked.svg
+unfold-hide     = typ_arrow-right.svg
+unfold-show     = typ_arrow-down.svg
 up              = typ_chevron-up.svg
 view            = typ_eye.svg
 view_build      = typ_export-grey.svg

novelwriter/assets/icons/typicons_light/typ_arrow-down.svg

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg width="24" height="24" version="1.2" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
+ <path d="m1.5077 8.1077 10.492 10.662 10.492-10.662c0.33846-0.33846 0.50769-0.84615 0.50769-1.1846 0-0.33846-0.16923-0.84615-0.50769-1.1846-0.33846-0.33846-0.67692-0.50769-1.1846-0.50769h-18.615c-0.50769 0-0.84615 0.16923-1.1846 0.50769-0.33846 0.33846-0.50769 0.84615-0.50769 1.1846 0 0.33846 0.16923 0.84615 0.50769 1.1846z" fill-opacity=".78039" stroke-width="1.6923"/>
+</svg>

novelwriter/assets/icons/typicons_light/typ_arrow-right.svg

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg width="24" height="24" version="1.2" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg">
+ <path d="m8.1077 22.492 10.662-10.492-10.662-10.492c-0.33846-0.33846-0.84615-0.50769-1.1846-0.50769-0.33846 0-0.84615 0.16923-1.1846 0.50769-0.33846 0.33846-0.50769 0.67692-0.50769 1.1846v18.615c0 0.50769 0.16923 0.84615 0.50769 1.1846 0.33846 0.33846 0.84615 0.50769 1.1846 0.50769 0.33846 0 0.84615-0.16923 1.1846-0.50769z" fill-opacity=".78039" stroke-width="1.6923"/>
+</svg>

novelwriter/constants.py

@@ -23,8 +23,6 @@ along with this program. If not, see <https://www.gnu.org/licenses/>.
 """
 from __future__ import annotations
 
-import re
-
 from PyQt5.QtCore import QCoreApplication, QT_TRANSLATE_NOOP
 
 from novelwriter.enum import nwBuildFmt, nwItemClass, nwItemLayout, nwOutline
@@ -70,9 +68,6 @@ class nwRegEx:
     FMT_SC = r"(?i)(?<!\\)(\[[\/\!]?(?:i|b|s|u|m|sup|sub)\])"
     FMT_SV = r"(?<!\\)(\[(?i)(?:fn|footnote):)(.+?)(?<!\\)(\])"
 
-    # Pre-Compiled RegEx
-    RX_SC = re.compile(FMT_SC)
-
 # END Class nwRegEx
 
 

novelwriter/core/docbuild.py

@@ -52,14 +52,15 @@ class NWBuildDocument:
     manuscript, based on a build definition object (BuildSettings).
     """
 
-    __slots__ = ("_project", "_build", "_queue", "_error", "_cache")
+    __slots__ = ("_project", "_build", "_queue", "_error", "_cache", "_count")
 
-    def __init__(self, project: NWProject, build: BuildSettings) -> None:
+    def __init__(self, project: NWProject, build: BuildSettings, doCount: bool = False) -> None:
         self._project = project
         self._build = build
         self._queue = []
         self._error = None
         self._cache = None
+        self._count = doCount
         return
 
     ##
@@ -314,11 +315,15 @@ class NWBuildDocument:
                     bldObj.addRootHeading(tHandle)
                     if convert:
                         bldObj.doConvert()
+                    if self._count:
+                        bldObj.countStats()
                 elif tItem.isFileType():
                     bldObj.setText(tHandle)
                     bldObj.doPreProcessing()
                     bldObj.tokenizeText()
                     bldObj.doHeaders()
+                    if self._count:
+                        bldObj.countStats()
                     if convert:
                         bldObj.doConvert()
                 else:

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
@@ -40,7 +39,8 @@ 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
@@ -266,7 +266,7 @@ 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)
@@ -400,7 +400,7 @@ class NWIndex:
 
     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
 
@@ -1315,86 +1315,3 @@ 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/tohtml.py

@@ -368,13 +368,12 @@ 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
         ))
@@ -384,7 +383,7 @@ 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],
@@ -449,6 +448,7 @@ 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;}")

novelwriter/core/tokenizer.py

@@ -110,6 +110,9 @@ class Tokenizer(ABC):
     A_IND_L    = 0x0100  # Left indentation
     A_IND_R    = 0x0200  # Right indentation
 
+    # Lookups
+    L_HEADINGS = [T_TITLE, T_UNNUM, T_HEAD1, T_HEAD2, T_HEAD3, T_HEAD4]
+
     def __init__(self, project: NWProject) -> None:
 
         self._project = project
@@ -118,6 +121,7 @@ class Tokenizer(ABC):
         self._text   = ""    # The raw text to be tokenized
         self._nwItem = None  # The NWItem currently being processed
         self._result = ""    # The result of the last document
+        self._counts = {}    # Counter data
 
         self._keepMarkdown = False  # Whether to keep the markdown text
         self._allMarkdown  = []     # The result novelWriter markdown of all documents
@@ -210,6 +214,11 @@ class Tokenizer(ABC):
         """The combined novelWriter Markdown text."""
         return self._allMarkdown
 
+    @property
+    def textStats(self) -> dict[str, int]:
+        """The collected stats about the text."""
+        return self._counts
+
     @property
     def errData(self) -> list:
         """The error data."""
@@ -751,6 +760,115 @@ class Tokenizer(ABC):
 
         return True
 
+    def countStats(self) -> dict[str, int]:
+        """Count stats on the tokenized text."""
+        titleCount = self._counts.get("titleCount", 0)
+        paragraphCount = self._counts.get("paragraphCount", 0)
+
+        allWords = self._counts.get("allWords", 0)
+        textWords = self._counts.get("textWords", 0)
+        titleWords = self._counts.get("titleWords", 0)
+
+        allChars = self._counts.get("allChars", 0)
+        textChars = self._counts.get("textChars", 0)
+        titleChars = self._counts.get("titleChars", 0)
+
+        allWordChars = self._counts.get("allWordChars", 0)
+        textWordChars = self._counts.get("textWordChars", 0)
+        titleWordChars = self._counts.get("titleWordChars", 0)
+
+        para = []
+        for tType, _, tText, _, _ in self._tokens:
+            tText = tText.replace(nwUnicode.U_ENDASH, " ")
+            tText = tText.replace(nwUnicode.U_EMDASH, " ")
+
+            tWords = tText.split()
+            nWords = len(tWords)
+            nChars = len(tText)
+            nWChars = len("".join(tWords))
+
+            if tType == self.T_EMPTY:
+                if len(para) > 0:
+                    tTemp = "\n".join(para)
+                    tPWords = tTemp.split()
+                    nPWords = len(tPWords)
+                    nPChars = len(tTemp)
+                    nPWChars = len("".join(tPWords))
+
+                    paragraphCount += 1
+                    allWords += nPWords
+                    textWords += nPWords
+                    allChars += nPChars
+                    textChars += nPChars
+                    allWordChars += nPWChars
+                    textWordChars += nPWChars
+                para = []
+
+            elif tType in self.L_HEADINGS:
+                titleCount += 1
+                allWords += nWords
+                titleWords += nWords
+                allChars += nChars
+                allWordChars += nWChars
+                titleChars += nChars
+                titleWordChars += nWChars
+
+            elif tType == self.T_SEP:
+                allWords += nWords
+                allChars += nChars
+                allWordChars += nWChars
+
+            elif tType == self.T_TEXT:
+                para.append(tText.rstrip())
+
+            elif tType == self.T_SYNOPSIS and self._doSynopsis:
+                text = "{0}: {1}".format(self._localLookup("Synopsis"), tText)
+                words = text.split()
+                allWords += len(words)
+                allChars += len(text)
+                allWordChars += len("".join(words))
+
+            elif tType == self.T_SHORT and self._doSynopsis:
+                text = "{0}: {1}".format(self._localLookup("Short Description"), tText)
+                words = text.split()
+                allWords += len(words)
+                allChars += len(text)
+                allWordChars += len("".join(words))
+
+            elif tType == self.T_COMMENT and self._doComments:
+                text = "{0}: {1}".format(self._localLookup("Comment"), tText)
+                words = text.split()
+                allWords += len(words)
+                allChars += len(text)
+                allWordChars += len("".join(words))
+
+            elif tType == self.T_KEYWORD and self._doKeywords:
+                valid, bits, _ = self._project.index.scanThis("@"+tText)
+                if valid and bits:
+                    key = self._localLookup(nwLabels.KEY_NAME[bits[0]])
+                    text = "{0}: {1}".format(key, ", ".join(bits[1:]))
+                    words = text.split()
+                    allWords += len(words)
+                    allChars += len(text)
+                    allWordChars += len("".join(words))
+
+        self._counts["titleCount"] = titleCount
+        self._counts["paragraphCount"] = paragraphCount
+
+        self._counts["allWords"] = allWords
+        self._counts["textWords"] = textWords
+        self._counts["titleWords"] = titleWords
+
+        self._counts["allChars"] = allChars
+        self._counts["textChars"] = textChars
+        self._counts["titleChars"] = titleChars
+
+        self._counts["allWordChars"] = allWordChars
+        self._counts["textWordChars"] = textWordChars
+        self._counts["titleWordChars"] = titleWordChars
+
+        return {}
+
     def saveRawMarkdown(self, path: str | Path) -> None:
         """Save the raw text to a plain text file."""
         with open(path, mode="w", encoding="utf-8") as outFile:

novelwriter/gui/doceditor.py

@@ -56,9 +56,9 @@ from novelwriter import CONFIG, SHARED
 from novelwriter.enum import nwDocAction, nwDocInsert, nwDocMode, nwItemClass, nwTrinary
 from novelwriter.common import minmax, transferCase
 from novelwriter.constants import nwKeyWords, nwLabels, nwShortcode, nwUnicode, trConst
-from novelwriter.core.index import countWords
 from novelwriter.tools.lipsum import GuiLipsum
 from novelwriter.core.document import NWDocument
+from novelwriter.text.counting import standardCounter
 from novelwriter.gui.dochighlight import GuiDocHighlighter
 from novelwriter.gui.editordocument import GuiTextDocument
 from novelwriter.extensions.eventfilters import WheelEventFilter
@@ -462,7 +462,7 @@ class GuiDocEditor(QPlainTextEdit):
             return False
 
         docText = self.getText()
-        cC, wC, pC = countWords(docText)
+        cC, wC, pC = standardCounter(docText)
         self._updateDocCounts(cC, wC, pC)
 
         self.saveCursorPosition()
@@ -2226,7 +2226,7 @@ class BackgroundWordCounter(QRunnable):
         else:
             text = self._docEditor.getText()
 
-        cC, wC, pC = countWords(text)
+        cC, wC, pC = standardCounter(text)
         self.signals.countsReady.emit(cC, wC, pC)
         self._isRunning = False
 

novelwriter/gui/theme.py

@@ -462,6 +462,7 @@ class GuiIcons:
         # Switches
         "sticky-on", "sticky-off",
         "bullet-on", "bullet-off",
+        "unfold-show", "unfold-hide",
 
         # Decorations
         "deco_doc_h0", "deco_doc_h1", "deco_doc_h2", "deco_doc_h3", "deco_doc_h4", "deco_doc_more",
@@ -472,6 +473,7 @@ class GuiIcons:
     TOGGLE_ICON_KEYS: dict[str, tuple[str, str]] = {
         "sticky": ("sticky-on", "sticky-off"),
         "bullet": ("bullet-on", "bullet-off"),
+        "unfold": ("unfold-show", "unfold-hide"),
     }
 
     IMAGE_MAP: dict[str, tuple[str, str]] = {

novelwriter/text/__init__.py

@@ -0,0 +1,3 @@
+"""
+novelWriter – Text Analysis Tools
+"""

novelwriter/text/counting.py

@@ -0,0 +1,135 @@
+"""
+novelWriter – Text Counting Functions
+=====================================
+
+File History:
+Created:   2019-04-22 [0.0.1] standardCounter
+Rewritten: 2024-02-27 [2.4b1] preProcessText, standardCounter
+Created:   2024-02-27 [2.4b1] bodyTextCounter
+
+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 re
+
+from novelwriter.constants import nwRegEx, nwUnicode
+
+RX_SC = re.compile(nwRegEx.FMT_SC)
+RX_LO = re.compile(r"(?i)(?<!\\)(\[(?:vspace|newpage|new page)(:\d+)?)(?<!\\)(\])")
+RX_IN = re.compile(r"^>{1,2}\s*|\s*<{1,2}$")
+
+
+def preProcessText(text: str, keepHeaders: bool = True) -> list[str]:
+    """Strip formatting codes from the text and split into lines."""
+    if not isinstance(text, str):
+        return []
+
+    # 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, " ")
+
+    ignore = "%@" if keepHeaders else "%@#"
+
+    result = []
+    for line in text.splitlines():
+        line = line.rstrip()
+        if line:
+            if line[0] in ignore:
+                continue
+            if line[0] == ">":
+                line = line.lstrip(">").lstrip(" ")
+            if line[-1] == "<":
+                line = line.rstrip("<").rstrip(" ")
+            if "[" in line:
+                # Strip shortcodes and special formatting
+                # RegEx is slow, so we do this only when necessary
+                line = RX_SC.sub("", line)
+                line = RX_LO.sub("", line)
+
+        result.append(line)
+
+    return result
+
+
+def standardCounter(text: str) -> tuple[int, int, int]:
+    """A counter that counts paragraphs, words and characters.
+    This is the standard counter that includes headers in the word and
+    character counts.
+    """
+    cCount = 0
+    wCount = 0
+    pCount = 0
+    prevEmpty = True
+
+    for line in preProcessText(text):
+
+        countPara = True
+        if not line:
+            prevEmpty = True
+            continue
+
+        if 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
+
+        wCount += len(line.split())
+        cCount += len(line)
+        if countPara and prevEmpty:
+            pCount += 1
+
+        prevEmpty = not countPara
+
+    return cCount, wCount, pCount
+
+
+def bodyTextCounter(text: str | list[str]) -> tuple[int, int, int]:
+    """A counter that counts body text words, characters, and characters
+    without white spaces.
+    """
+    wCount = 0
+    cCount = 0
+    sCount = 0
+
+    for line in preProcessText(text, keepHeaders=False):
+        words = line.split()
+        wCount += len(words)
+        cCount += len(line)
+        sCount += len("".join(words))
+
+    return wCount, cCount, sCount

novelwriter/tools/manuscript.py

@@ -33,9 +33,10 @@ from datetime import datetime
 from PyQt5.QtGui import QCloseEvent, QColor, QCursor, QFont, QPalette, QResizeEvent
 from PyQt5.QtCore import QSize, QTimer, Qt, pyqtSlot
 from PyQt5.QtWidgets import (
-    QAbstractItemView, QDialog, QGridLayout, QHBoxLayout, QLabel, QListWidget,
+    QAbstractItemView, QDialog, QFormLayout, QGridLayout, QHBoxLayout, QLabel,
-    QListWidgetItem, QPushButton, QSplitter, QTextBrowser, QToolButton,
+    QListWidget, QListWidgetItem, QPushButton, QSizePolicy, QSplitter,
-    QTreeWidget, QTreeWidgetItem, QVBoxLayout, QWidget, qApp
+    QStackedWidget, QTextBrowser, QToolButton, QTreeWidget, QTreeWidgetItem,
+    QVBoxLayout, QWidget, qApp
 )
 from PyQt5.QtPrintSupport import QPrintPreviewDialog, QPrinter
 
@@ -185,6 +186,15 @@ class GuiManuscript(QDialog):
         # ============
 
         self.docPreview = _PreviewWidget(self)
+        self.docStats = _StatsWidget(self)
+
+        self.docBox = QVBoxLayout()
+        self.docBox.addWidget(self.docPreview, 1)
+        self.docBox.addWidget(self.docStats, 0)
+        self.docBox.setContentsMargins(0, 0, 0, 0)
+
+        self.docWdiget = QWidget(self)
+        self.docWdiget.setLayout(self.docBox)
 
         self.controlBox = QVBoxLayout()
         self.controlBox.addLayout(self.listToolBox, 0)
@@ -192,12 +202,12 @@ class GuiManuscript(QDialog):
         self.controlBox.addLayout(self.processBox, 0)
         self.controlBox.setContentsMargins(0, 0, 0, 0)
 
-        self.optsWidget = QWidget()
+        self.optsWidget = QWidget(self)
         self.optsWidget.setLayout(self.controlBox)
 
         self.mainSplit = QSplitter()
         self.mainSplit.addWidget(self.optsWidget)
-        self.mainSplit.addWidget(self.docPreview)
+        self.mainSplit.addWidget(self.docWdiget)
         self.mainSplit.setCollapsible(0, False)
         self.mainSplit.setCollapsible(1, False)
         self.mainSplit.setStretchFactor(0, 0)
@@ -245,7 +255,7 @@ class GuiManuscript(QDialog):
                 if isinstance(build, BuildSettings):
                     self._updatePreview(data, build)
             except Exception:
-                logger.error("Failed to save build cache")
+                logger.error("Failed to load build cache")
                 logException()
                 return
 
@@ -327,7 +337,7 @@ class GuiManuscript(QDialog):
         if build is None:
             return
 
-        docBuild = NWBuildDocument(SHARED.project, build)
+        docBuild = NWBuildDocument(SHARED.project, build, doCount=True)
         docBuild.queueAll()
 
         self.docPreview.beginNewBuild(len(docBuild))
@@ -340,6 +350,7 @@ class GuiManuscript(QDialog):
         result = {
             "uuid": build.buildID,
             "time": int(time()),
+            "stats": buildObj.textStats,
             "styles": buildObj.getStyleSheet(),
             "html": buildObj.fullHTML,
         }
@@ -395,6 +406,7 @@ class GuiManuscript(QDialog):
         self.docPreview.setJustify(
             build.getBool("format.justifyText")
         )
+        self.docStats.updateStats(data.get("stats", {}))
         return
 
     def _getSelectedBuild(self) -> BuildSettings | None:
@@ -756,20 +768,13 @@ class _PreviewWidget(QTextBrowser):
         self.buildProgress.setCentreText(self.tr("Processing ..."))
         qApp.processEvents()
 
-        styles = "\n".join(data.get("styles", [
+        styles = "\n".join(data.get("styles", []))
-            "h1, h2 {color: rgb(66, 113, 174);}",
-            "h3, h4 {color: rgb(50, 50, 50);}",
-            "a {color: rgb(66, 113, 174);}",
-            ".tags {color: rgb(245, 135, 31); font-weight: bold;}",
-        ]))
         self.document().setDefaultStyleSheet(styles)
 
         html = "".join(data.get("html", []))
         html = html.replace("\t", "!!tab!!")
         html = html.replace("<del>", "<span style='text-decoration: line-through;'>")
         html = html.replace("</del>", "</span>")
-        html = html.replace("<mark>", "<span style='background-color: #ffffa6;'>")
-        html = html.replace("</mark>", "</span>")
         self.setHtml(html)
         qApp.processEvents()
         while self.find("!!tab!!"):
@@ -861,3 +866,195 @@ class _PreviewWidget(QTextBrowser):
         return
 
 # END Class _PreviewWidget
+
+
+class _StatsWidget(QWidget):
+
+    def __init__(self, parent: QWidget) -> None:
+        super().__init__(parent=parent)
+
+        font = self.font()
+        font.setPointSizeF(0.9*SHARED.theme.fontPointSize)
+        self.setFont(font)
+
+        self.minWidget = QWidget(self)
+        self.maxWidget = QWidget(self)
+
+        fPx = int(0.6*SHARED.theme.fontPixelSize)
+        toggleIcon = SHARED.theme.getToggleIcon("unfold", (fPx, fPx))
+
+        fadeCol = self.palette().text().color()
+        buttonStyle = (
+            "QToolButton {{padding: 0; border: none; background: transparent;}} "
+            "QToolButton:hover {{border: none; background: rgba({0},{1},{2},0.2);}}"
+        ).format(fadeCol.red(), fadeCol.green(), fadeCol.blue())
+
+        self.toggleButton = QToolButton(self)
+        self.toggleButton.setCheckable(True)
+        self.toggleButton.setIcon(toggleIcon)
+        self.toggleButton.setStyleSheet(buttonStyle)
+        self.toggleButton.toggled.connect(self._toggleView)
+
+        self._buildMinimal()
+        self._buildMaximal()
+
+        self.mainStack = QStackedWidget(self)
+        self.mainStack.addWidget(self.minWidget)
+        self.mainStack.addWidget(self.maxWidget)
+
+        self.outerBox = QHBoxLayout()
+        self.outerBox.addWidget(self.toggleButton, 0, Qt.AlignmentFlag.AlignTop)
+        self.outerBox.addWidget(self.mainStack, 1, Qt.AlignmentFlag.AlignTop)
+        self.outerBox.setContentsMargins(0, 0, 0, 0)
+
+        self.setLayout(self.outerBox)
+
+        self._toggleView(False)
+
+        return
+
+    def updateStats(self, data: dict[str, int]) -> None:
+        """Update the stats values from a Tokenizer stats dict."""
+        # Minimal
+        self.minWordCount.setText("{0:n}".format(data.get("allWords", 0)))
+        self.minCharCount.setText("{0:n}".format(data.get("allChars", 0)))
+
+        # Maximal
+        self.maxTotalWords.setText("{0:n}".format(data.get("allWords", 0)))
+        self.maxHeaderWords.setText("{0:n}".format(data.get("titleWords", 0)))
+        self.maxTextWords.setText("{0:n}".format(data.get("textWords", 0)))
+        self.maxTitleCount.setText("{0:n}".format(data.get("titleCount", 0)))
+        self.maxParCount.setText("{0:n}".format(data.get("paragraphCount", 0)))
+
+        self.maxTotalChars.setText("{0:n}".format(data.get("allChars", 0)))
+        self.maxHeaderChars.setText("{0:n}".format(data.get("titleChars", 0)))
+        self.maxTextChars.setText("{0:n}".format(data.get("textChars", 0)))
+
+        self.maxTotalWordChars.setText("{0:n}".format(data.get("allWordChars", 0)))
+        self.maxHeaderWordChars.setText("{0:n}".format(data.get("titleWordChars", 0)))
+        self.maxTextWordChars.setText("{0:n}".format(data.get("textWordChars", 0)))
+
+        return
+
+    ##
+    #  Private Slots
+    ##
+
+    @pyqtSlot(bool)
+    def _toggleView(self, state: bool) -> None:
+        """Toggle minimal or maximal view."""
+        ignored = QSizePolicy.Policy.Ignored
+        expanded = QSizePolicy.Policy.Expanding
+        if state:
+            self.mainStack.setCurrentWidget(self.maxWidget)
+            self.maxWidget.setSizePolicy(expanded, expanded)
+            self.minWidget.setSizePolicy(ignored, ignored)
+        else:
+            self.mainStack.setCurrentWidget(self.minWidget)
+            self.maxWidget.setSizePolicy(ignored, ignored)
+            self.minWidget.setSizePolicy(expanded, expanded)
+        self.maxWidget.adjustSize()
+        self.minWidget.adjustSize()
+        self.mainStack.adjustSize()
+        self.adjustSize()
+        return
+
+    ##
+    #  Internal Functions
+    ##
+
+    def _buildMinimal(self) -> None:
+        """Build the minimal stats page."""
+        mPx = CONFIG.pxInt(8)
+
+        self.lblWordCount = QLabel(self.tr("Words:"))
+        self.minWordCount = QLabel(self)
+
+        self.lblCharCount = QLabel(self.tr("Characters:"))
+        self.minCharCount = QLabel(self)
+
+        # Assemble
+        self.minLayout = QHBoxLayout()
+        self.minLayout.addWidget(self.lblWordCount)
+        self.minLayout.addWidget(self.minWordCount)
+        self.minLayout.addSpacing(mPx)
+        self.minLayout.addWidget(self.lblCharCount)
+        self.minLayout.addWidget(self.minCharCount)
+        self.minLayout.addStretch(1)
+        self.minLayout.setSpacing(mPx)
+        self.minLayout.setContentsMargins(0, 0, 0, 0)
+
+        self.minWidget.setLayout(self.minLayout)
+
+        return
+
+    def _buildMaximal(self) -> None:
+        """Build the maximal stats page."""
+        hPx = CONFIG.pxInt(12)
+        vPx = CONFIG.pxInt(4)
+
+        alignRight = Qt.AlignmentFlag.AlignRight
+
+        # Left Column
+        self.maxTotalWords = QLabel(self)
+        self.maxHeaderWords = QLabel(self)
+        self.maxTextWords = QLabel(self)
+        self.maxTitleCount = QLabel(self)
+        self.maxParCount = QLabel(self)
+
+        self.maxTotalWords.setAlignment(alignRight)
+        self.maxHeaderWords.setAlignment(alignRight)
+        self.maxTextWords.setAlignment(alignRight)
+        self.maxTitleCount.setAlignment(alignRight)
+        self.maxParCount.setAlignment(alignRight)
+
+        self.leftForm = QFormLayout()
+        self.leftForm.addRow(self.tr("Words:"), self.maxTotalWords)
+        self.leftForm.addRow(self.tr("Header Words:"), self.maxHeaderWords)
+        self.leftForm.addRow(self.tr("Body Text Words:"), self.maxTextWords)
+        self.leftForm.addRow("", QLabel(self))
+        self.leftForm.addRow(self.tr("Headers:"), self.maxTitleCount)
+        self.leftForm.addRow(self.tr("Paragraphs:"), self.maxParCount)
+        self.leftForm.setHorizontalSpacing(hPx)
+        self.leftForm.setVerticalSpacing(vPx)
+
+        # Right Column
+        self.maxTotalChars = QLabel(self)
+        self.maxHeaderChars = QLabel(self)
+        self.maxTextChars = QLabel(self)
+
+        self.maxTotalWordChars = QLabel(self)
+        self.maxHeaderWordChars = QLabel(self)
+        self.maxTextWordChars = QLabel(self)
+
+        self.maxTotalChars.setAlignment(alignRight)
+        self.maxHeaderChars.setAlignment(alignRight)
+        self.maxTextChars.setAlignment(alignRight)
+
+        self.maxTotalWordChars.setAlignment(alignRight)
+        self.maxHeaderWordChars.setAlignment(alignRight)
+        self.maxTextWordChars.setAlignment(alignRight)
+
+        self.rightForm = QFormLayout()
+        self.rightForm.addRow(self.tr("Characters:"), self.maxTotalChars)
+        self.rightForm.addRow(self.tr("Header Characters:"), self.maxHeaderChars)
+        self.rightForm.addRow(self.tr("Body Text Characters:"), self.maxTextChars)
+        self.rightForm.addRow(self.tr("Characters, No Spaces:"), self.maxTotalWordChars)
+        self.rightForm.addRow(self.tr("Header Characters, No Spaces:"), self.maxHeaderWordChars)
+        self.rightForm.addRow(self.tr("Body Text Characters, No Spaces:"), self.maxTextWordChars)
+        self.rightForm.setHorizontalSpacing(hPx)
+        self.rightForm.setVerticalSpacing(vPx)
+
+        # Assemble
+        self.maxLayout = QHBoxLayout()
+        self.maxLayout.addLayout(self.leftForm)
+        self.maxLayout.addLayout(self.rightForm)
+        self.maxLayout.addStretch(1)
+        self.maxLayout.setSpacing(CONFIG.pxInt(32))
+        self.maxLayout.setContentsMargins(0, 0, 0, 0)
+
+        self.maxWidget.setLayout(self.maxLayout)
+
+        return
+
+# END Class _StatsWidget

requirements-dev.txt

@@ -0,0 +1,2 @@
+flake8
+flake8-pep585

tests/reference/mBuildDocBuild_HTML5_Lorem_Ipsum.htm

@@ -14,6 +14,7 @@ h4 {color: rgb(50, 50, 50); page-break-after: avoid; margin-top: 0.76em; margin-
 .title {font-size: 2.5em; margin-top: 1.30em; margin-bottom: 0.65em;}
 .sep, .skip {text-align: center; margin-top: 1.30em; margin-bottom: 1.30em;}
 a {color: rgb(66, 113, 174);}
+mark {background: rgb(255, 255, 166);}
 .tags {color: rgb(245, 135, 31); font-weight: bold;}
 .break {text-align: left;}
 .synopsis {font-style: italic;}

tests/reference/mBuildDocBuild_HTML5_Lorem_Ipsum.json

@@ -2,8 +2,8 @@
   "meta": {
     "projectName": "Lorem Ipsum",
     "novelAuthor": "lipsum.com",
-    "buildTime": 1706648755,
+    "buildTime": 1709024252,
-    "buildTimeStr": "2024-01-30 22:05:55"
+    "buildTimeStr": "2024-02-27 09:57:32"
   },
   "text": {
     "css": [
@@ -16,6 +16,7 @@
       ".title {font-size: 2.5em; margin-top: 1.30em; margin-bottom: 0.65em;}",
       ".sep, .skip {text-align: center; margin-top: 1.30em; margin-bottom: 1.30em;}",
       "a {color: rgb(66, 113, 174);}",
+      "mark {background: rgb(255, 255, 166);}",
       ".tags {color: rgb(245, 135, 31); font-weight: bold;}",
       ".break {text-align: left;}",
       ".synopsis {font-style: italic;}",

tests/test_core/test_core_docbuild.py

@@ -83,7 +83,7 @@ def testCoreDocBuild_OpenDocument(monkeypatch, mockGUI, prjLipsum, fncPath, tstP
     build = BuildSettings()
     build.unpack(BUILD_CONF)
 
-    docBuild = NWBuildDocument(project, build)
+    docBuild = NWBuildDocument(project, build, doCount=True)
     docBuild.queueAll()
 
     assert len(docBuild) == 21

tests/test_core/test_core_index.py

@@ -31,7 +31,7 @@ from tools import C, buildTestProject, cmpFiles, writeFile
 
 from novelwriter.enum import nwComment, nwItemClass, nwItemLayout
 from novelwriter.constants import nwFiles
-from novelwriter.core.index import IndexItem, NWIndex, countWords, TagsIndex, processComment
+from novelwriter.core.index import IndexItem, NWIndex, TagsIndex, processComment
 from novelwriter.core.project import NWProject
 
 
@@ -1319,105 +1319,3 @@ def testCoreIndex_processComment():
     assert processComment("% \t  SHORT  : Hi:You") == (nwComment.SHORT, "Hi:You", 13)
 
 # END Test testCoreIndex_processComment
-
-
-@pytest.mark.core
-def testCoreIndex_countWords():
-    """Test the word counter and the exclusion filers."""
-    # Non-Text
-    assert countWords(None) == (0, 0, 0)  # type: ignore
-    assert countWords(1234) == (0, 0, 0)  # type: ignore
-
-    # General Text
-    cC, wC, pC = countWords((
-        "# Heading One\n"
-        "## Heading Two\n"
-        "### Heading Three\n"
-        "#### Heading Four\n\n"
-        "@tag: value\n\n"
-        "% A comment that should not be counted.\n\n"
-        "The first paragraph.\n\n"
-        "The second paragraph.\n\n\n"
-        "The third paragraph.\n\n"
-        "Dashes\u2013and even longer\u2014dashes."
-    ))
-    assert cC == 138
-    assert wC == 22
-    assert pC == 4
-
-    # Text Alignment
-    cC, wC, pC = countWords((
-        "# Title\n\n"
-        "Left aligned<<\n\n"
-        "Left aligned <<\n\n"
-        "Right indent<\n\n"
-        "Right indent <\n\n"
-    ))
-    assert cC == 53
-    assert wC == 9
-    assert pC == 4
-
-    cC, wC, pC = countWords((
-        "# Title\n\n"
-        ">>Right aligned\n\n"
-        ">> Right aligned\n\n"
-        ">Left indent\n\n"
-        "> Left indent\n\n"
-    ))
-    assert cC == 53
-    assert wC == 9
-    assert pC == 4
-
-    cC, wC, pC = countWords((
-        "# Title\n\n"
-        ">>Centre aligned<<\n\n"
-        ">> Centre aligned <<\n\n"
-        ">Double indent<\n\n"
-        "> Double indent <\n\n"
-    ))
-    assert cC == 59
-    assert wC == 9
-    assert pC == 4
-
-    # Formatting Codes, Upper Case (Old Implementation)
-    cC, wC, pC = countWords((
-        "Some text\n\n"
-        "[NEWPAGE]\n\n"
-        "more text\n\n"
-        "[NEW PAGE]]\n\n"
-        "even more text\n\n"
-        "[VSPACE]\n\n"
-        "and some final text\n\n"
-        "[VSPACE:4]\n\n"
-        "THE END\n\n"
-    ))
-    assert cC == 58
-    assert wC == 13
-    assert pC == 5
-
-    # Formatting Codes, Lower Case (Current Implementation)
-    cC, wC, pC = countWords((
-        "Some text\n\n"
-        "[newpage]\n\n"
-        "more text\n\n"
-        "[new page]]\n\n"
-        "even more text\n\n"
-        "[vspace]\n\n"
-        "and some final text\n\n"
-        "[vspace:4]\n\n"
-        "THE END\n\n"
-    ))
-    assert cC == 58
-    assert wC == 13
-    assert pC == 5
-
-    # Check ShortCodes
-    cC, wC, pC = countWords((
-        "Text with [b]bold[/b] text and padded [b] bold [/b] text.\n\n"
-        "Text with [b][i] nested [/i] emphasis [/b] in it.\n\n"
-    ))
-    assert cC == 78
-    assert wC == 14
-    assert pC == 2
-
-# END Test testCoreIndex_countWords

tests/test_core/test_core_tokenizer.py

@@ -1253,6 +1253,225 @@ def testCoreToken_ProcessHeaders(mockGUI):
 # END Test testCoreToken_ProcessHeaders
 
 
+@pytest.mark.core
+def testCoreToken_CountStats(mockGUI, ipsumText):
+    """Test stats counter of the Tokenizer class."""
+    project = NWProject()
+    project.data.setLanguage("en")
+    project._loadProjectLocalisation()
+    tokens = BareTokenizer(project)
+    tokens._isNone  = False
+    tokens._isNote  = False
+    tokens._isNovel = True
+
+    # Short Text
+    # ==========
+
+    # Header wo/Format
+    tokens._text = "## A Chapter Title\n\n"
+    tokens._counts = {}
+    tokens.tokenizeText()
+    tokens.doHeaders()
+    tokens.countStats()
+    assert tokens._tokens[0][2] == "A Chapter Title"
+    assert tokens.textStats == {
+        "titleCount": 1, "paragraphCount": 0,
+        "allWords": 3, "textWords": 0, "titleWords": 3,
+        "allChars": 15, "textChars": 0, "titleChars": 15,
+        "allWordChars": 13, "textWordChars": 0, "titleWordChars": 13
+    }
+
+    # Header w/Format
+    tokens._text = "## A Chapter Title\n\n"
+    tokens._counts = {}
+    tokens.setChapterFormat(f"C {nwHeadFmt.CH_NUM}: {nwHeadFmt.TITLE}")
+    tokens._hFormatter.resetAll()
+    tokens.tokenizeText()
+    tokens.doHeaders()
+    tokens.countStats()
+    assert tokens._tokens[0][2] == "C 1: A Chapter Title"
+    assert tokens.textStats == {
+        "titleCount": 1, "paragraphCount": 0,
+        "allWords": 5, "textWords": 0, "titleWords": 5,
+        "allChars": 20, "textChars": 0, "titleChars": 20,
+        "allWordChars": 16, "textWordChars": 0, "titleWordChars": 16
+    }
+
+    # Two Paragraphs
+    # First break should be counted, the double breaks not.
+    tokens._text = "Some text\non two lines.\n\nWith a second paragraph.\n\n"
+    tokens._counts = {}
+    tokens.tokenizeText()
+    tokens.doHeaders()
+    tokens.countStats()
+    assert tokens.textStats == {
+        "titleCount": 0, "paragraphCount": 2,
+        "allWords": 9, "textWords": 9, "titleWords": 0,
+        "allChars": 47, "textChars": 47, "titleChars": 0,
+        "allWordChars": 40, "textWordChars": 40, "titleWordChars": 0
+    }
+
+    # Two Scenes w/Separator
+    tokens._text = "## Chapter\n\n### Scene\n\nText\n\n### Scene\n\nText"
+    tokens._counts = {}
+    tokens.setChapterFormat(nwHeadFmt.TITLE)
+    tokens.setSceneFormat("* * *", False)
+    tokens.tokenizeText()
+    tokens.doHeaders()
+    tokens.countStats()
+    assert [t[2] for t in tokens._tokens] == [
+        "Chapter", "", "", "", "Text", "", "* * *", "", "Text", ""
+    ]
+    assert tokens.textStats == {
+        "titleCount": 1, "paragraphCount": 2,
+        "allWords": 6, "textWords": 2, "titleWords": 1,
+        "allChars": 20, "textChars": 8, "titleChars": 7,
+        "allWordChars": 18, "textWordChars": 8, "titleWordChars": 7
+    }
+
+    # Scene w/Synopsis
+    # Synopsis does not count as a paragraph, and counts as "Synopsis: Stuff"
+    tokens._text = "## Chapter\n\n### Scene\n\n%Synopsis: Stuff\n\nText"
+    tokens._counts = {}
+    tokens.setChapterFormat(nwHeadFmt.TITLE)
+    tokens.setSceneFormat("* * *", False)
+    tokens.setSynopsis(True)
+    tokens.tokenizeText()
+    tokens.doHeaders()
+    tokens.countStats()
+    assert [t[2] for t in tokens._tokens] == [
+        "Chapter", "", "", "", "Stuff", "", "Text", ""
+    ]
+    assert tokens.textStats == {
+        "titleCount": 1, "paragraphCount": 1,
+        "allWords": 4, "textWords": 1, "titleWords": 1,
+        "allChars": 26, "textChars": 4, "titleChars": 7,
+        "allWordChars": 25, "textWordChars": 4, "titleWordChars": 7
+    }
+
+    # Scene w/Short
+    # Short does not count as a paragraph, and counts as "Short Description: Stuff"
+    tokens._text = "## Chapter\n\n### Scene\n\n%Short: Stuff\n\nText"
+    tokens._counts = {}
+    tokens.setChapterFormat(nwHeadFmt.TITLE)
+    tokens.setSceneFormat("* * *", False)
+    tokens.setSynopsis(True)
+    tokens.tokenizeText()
+    tokens.doHeaders()
+    tokens.countStats()
+    assert [t[2] for t in tokens._tokens] == [
+        "Chapter", "", "", "", "Stuff", "", "Text", ""
+    ]
+    assert tokens.textStats == {
+        "titleCount": 1, "paragraphCount": 1,
+        "allWords": 5, "textWords": 1, "titleWords": 1,
+        "allChars": 35, "textChars": 4, "titleChars": 7,
+        "allWordChars": 33, "textWordChars": 4, "titleWordChars": 7
+    }
+
+    # Scene w/Comment
+    # Comment does not count as a paragraph, and counts as "Comment: Stuff"
+    tokens._text = "## Chapter\n\n### Scene\n\n% Stuff\n\nText"
+    tokens._counts = {}
+    tokens.setChapterFormat(nwHeadFmt.TITLE)
+    tokens.setSceneFormat("* * *", False)
+    tokens.setComments(True)
+    tokens.tokenizeText()
+    tokens.doHeaders()
+    tokens.countStats()
+    assert [t[2] for t in tokens._tokens] == [
+        "Chapter", "", "", "", "Stuff", "", "Text", ""
+    ]
+    assert tokens.textStats == {
+        "titleCount": 1, "paragraphCount": 1,
+        "allWords": 4, "textWords": 1, "titleWords": 1,
+        "allChars": 25, "textChars": 4, "titleChars": 7,
+        "allWordChars": 24, "textWordChars": 4, "titleWordChars": 7
+    }
+
+    # Scene w/Keyword
+    # Keyword does not count as a paragraph, and counts as "Point of View: Jane"
+    tokens._text = "## Chapter\n\n### Scene\n\n@pov: Jane\n\nText"
+    tokens._counts = {}
+    tokens.setChapterFormat(nwHeadFmt.TITLE)
+    tokens.setSceneFormat("* * *", False)
+    tokens.setKeywords(True)
+    tokens.tokenizeText()
+    tokens.doHeaders()
+    tokens.countStats()
+    assert [t[2] for t in tokens._tokens] == [
+        "Chapter", "", "", "", "pov: Jane", "", "Text", ""
+    ]
+    assert tokens.textStats == {
+        "titleCount": 1, "paragraphCount": 1,
+        "allWords": 6, "textWords": 1, "titleWords": 1,
+        "allChars": 30, "textChars": 4, "titleChars": 7,
+        "allWordChars": 27, "textWordChars": 4, "titleWordChars": 7
+    }
+
+    # Long Text
+    # =========
+    tokens._text = (
+        "# Act One\n\n"
+
+        "## Chapter\n\n"
+
+        "### Scene\n\n"
+        "@pov: Jane\n"
+        "@char: Jane, John\n\n"
+        "%Synopsis: A scene\n\n"
+        f"{ipsumText[0]}.\n\n"
+
+        "### Scene\n\n"
+        "@pov: Jane\n"
+        "@char: Jane, John\n\n"
+        "%Synopsis: A scene\n\n"
+        f"{ipsumText[1]}.\n\n"
+
+        "## Chapter\n\n"
+
+        "### Scene\n\n"
+        "@pov: Jane\n"
+        "@char: Jane, John\n\n"
+        "%Synopsis: A scene\n\n"
+        f"{ipsumText[2]}.\n\n"
+
+        "### Scene\n\n"
+        "@pov: Jane\n"
+        "@char: Jane, John\n\n"
+        "%Synopsis: A scene\n\n"
+        f"{ipsumText[3]}.\n\n"
+
+        "## Chapter\n\n"
+
+        "### Scene\n\n"
+        "@pov: Jane\n"
+        "@char: Jane, John\n\n"
+        "%Synopsis: A scene\n\n"
+        f"{ipsumText[4]}.\n\n"
+    )
+    tokens._counts = {}
+
+    tokens.setTitleFormat(f"T: {nwHeadFmt.TITLE}")
+    tokens.setChapterFormat(f"C {nwHeadFmt.CH_NUM}: {nwHeadFmt.TITLE}")
+    tokens.setSceneFormat("* * *", False)
+    tokens.setSynopsis(True)
+    tokens.setComments(True)
+    tokens.setKeywords(True)
+
+    tokens.tokenizeText()
+    tokens.doHeaders()
+    tokens.countStats()
+    assert tokens.textStats == {
+        "titleCount": 4, "paragraphCount": 5,
+        "allWords": 596, "textWords": 528, "titleWords": 12,
+        "allChars": 3859, "textChars": 3513, "titleChars": 46,
+        "allWordChars": 3289, "textWordChars": 2990, "titleWordChars": 38
+    }
+
+# END Test testCoreToken_CountStats
+
+
 @pytest.mark.core
 def testCoreToken_HeaderCounterAndVisibility(mockGUI):
     """Test the header counter and visibility of the Tokenizer class.

tests/test_gui/test_gui_doceditor.py

@@ -32,8 +32,8 @@ from PyQt5.QtWidgets import QAction, QMenu, qApp
 from novelwriter import CONFIG, SHARED
 from novelwriter.enum import nwDocAction, nwDocInsert, nwItemLayout, nwTrinary, nwWidget
 from novelwriter.constants import nwKeyWords, nwUnicode
-from novelwriter.core.index import countWords
 from novelwriter.gui.doceditor import GuiDocEditor, GuiDocToolBar
+from novelwriter.text.counting import standardCounter
 from novelwriter.dialogs.editlabel import GuiEditLabel
 
 KEY_DELAY = 1
@@ -1673,7 +1673,7 @@ def testGuiEditor_WordCounters(qtbot, monkeypatch, nwGUI, projPath, ipsumText, m
     assert nwGUI.openDocument(C.hSceneDoc) is True
 
     text = "\n\n".join(ipsumText)
-    cC, wC, pC = countWords(text)
+    cC, wC, pC = standardCounter(text)
     nwGUI.docEditor.replaceText(text)
 
     # Check that a busy counter is blocked

tests/test_text/test_core_counting.py

@@ -0,0 +1,206 @@
+"""
+novelWriter – Counter Module Tester
+===================================
+
+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 pytest
+
+from novelwriter.text.counting import bodyTextCounter, preProcessText, standardCounter
+
+
+@pytest.mark.core
+def testTextCounting_preProcessText():
+    """Test the text preprocessor for counters."""
+    # Not Text
+    assert preProcessText(None) == []
+
+    # No Text
+    assert preProcessText("") == []
+
+    text = (
+        "#! Title\n"
+        "##! Prologue\n"
+        "# Heading One\n"
+        "## Heading Two\n"
+        "### Heading Three\n"
+        "#### Heading Four\n\n"
+        "@tag: value\n\n"
+        "% A comment.\n\n"
+        "A [b]paragraph[/b].\n\n"
+        "[vspace:3]\n\n"
+        "[New Page]\n\n"
+        "Dashes\u2013and even longer\u2014dashes.\n\n"
+    )
+
+    # Process Text, w/Headers
+    assert preProcessText(text) == [
+        "#! Title",
+        "##! Prologue",
+        "# Heading One",
+        "## Heading Two",
+        "### Heading Three",
+        "#### Heading Four",
+        "", "", "",
+        "A paragraph.", "",
+        "", "", "", "",
+        "Dashes and even longer dashes.", ""
+    ]
+
+    # Process Text, wo/Headers
+    assert preProcessText(text, keepHeaders=False) == [
+        "", "", "",
+        "A paragraph.", "",
+        "", "", "", "",
+        "Dashes and even longer dashes.", ""
+    ]
+
+# END Test testTextCounting_preProcessText
+
+
+@pytest.mark.core
+def testTextCounting_standardCounter():
+    """Test the standard counter."""
+    # Non-Text
+    assert standardCounter(None) == (0, 0, 0)  # type: ignore
+    assert standardCounter(1234) == (0, 0, 0)  # type: ignore
+
+    # General Text
+    cC, wC, pC = standardCounter((
+        "#! Title\n\n"
+        "##! Prologue\n\n"
+        "# Heading One\n"
+        "## Heading Two\n"
+        "### Heading Three\n"
+        "#### Heading Four\n\n"
+        "@tag: value\n\n"
+        "% A comment that should not be counted.\n\n"
+        "The first paragraph.\n\n"
+        "The second paragraph.\n\n\n"
+        "The third paragraph.\n\n"
+        "Dashes\u2013and even longer\u2014dashes."
+    ))
+    assert cC == 151
+    assert wC == 24
+    assert pC == 4
+
+    # Text Alignment
+    cC, wC, pC = standardCounter((
+        "# Title\n\n"
+        "Left aligned<<\n\n"
+        "Left aligned <<\n\n"
+        "Right indent<\n\n"
+        "Right indent <\n\n"
+    ))
+    assert cC == 53
+    assert wC == 9
+    assert pC == 4
+
+    cC, wC, pC = standardCounter((
+        "# Title\n\n"
+        ">>Right aligned\n\n"
+        ">> Right aligned\n\n"
+        ">Left indent\n\n"
+        "> Left indent\n\n"
+    ))
+    assert cC == 53
+    assert wC == 9
+    assert pC == 4
+
+    cC, wC, pC = standardCounter((
+        "# Title\n\n"
+        ">>Centre aligned<<\n\n"
+        ">> Centre aligned <<\n\n"
+        ">Double indent<\n\n"
+        "> Double indent <\n\n"
+    ))
+    assert cC == 59
+    assert wC == 9
+    assert pC == 4
+
+    # Formatting Codes, Upper Case (Old Implementation)
+    cC, wC, pC = standardCounter((
+        "Some text\n\n"
+        "[NEWPAGE]\n\n"
+        "more text\n\n"
+        "[NEW PAGE]\n\n"
+        "even more text\n\n"
+        "[VSPACE]\n\n"
+        "and some final text\n\n"
+        "[VSPACE:4]\n\n"
+        "THE END\n\n"
+    ))
+    assert cC == 58
+    assert wC == 13
+    assert pC == 5
+
+    # Formatting Codes, Lower Case (Current Implementation)
+    cC, wC, pC = standardCounter((
+        "Some text\n\n"
+        "[newpage]\n\n"
+        "more text\n\n"
+        "[new page]\n\n"
+        "even more text\n\n"
+        "[vspace]\n\n"
+        "and some final text\n\n"
+        "[vspace:4]\n\n"
+        "THE END\n\n"
+    ))
+    assert cC == 58
+    assert wC == 13
+    assert pC == 5
+
+    # Check ShortCodes
+    cC, wC, pC = standardCounter((
+        "Text with [b]bold[/b] text and padded [b] bold [/b] text.\n\n"
+        "Text with [b][i] nested [/i] emphasis [/b] in it.\n\n"
+    ))
+    assert cC == 78
+    assert wC == 14
+    assert pC == 2
+
+# END Test testTextCounting_standardCounter
+
+
+@pytest.mark.core
+def testTextCounting_bodyTextCounter():
+    """Test the body text counter."""
+    # Not Text
+    assert bodyTextCounter(None) == (0, 0, 0)
+
+    # General Text
+    wC, cC, sC = bodyTextCounter((
+        "#! Title\n\n"
+        "##! Prologue\n\n"
+        "# Heading One\n"
+        "## Heading Two\n"
+        "### Heading Three\n"
+        "#### Heading Four\n\n"
+        "@tag: value\n\n"
+        "% A comment that should not be counted.\n\n"
+        "The first paragraph.\n\n"
+        "The second paragraph.\n\n\n"
+        "The third paragraph.\n\n"
+        "Dashes\u2013and even longer\u2014dashes."
+    ))
+    assert wC == 14
+    assert cC == 91
+    assert sC == 81
+
+# END Test testTextCounting_bodyTextCounter

tests/test_tools/test_tools_manuscript.py

@@ -192,6 +192,16 @@ def testManuscript_Features(monkeypatch, qtbot: QtBot, nwGUI: GuiMain, projPath:
     assert manus.docPreview.toPlainText().strip() != ""
     assert cacheFile.exists() is True
 
+    # Check Preview Stats
+    assert manus.docStats.mainStack.currentWidget() == manus.docStats.minWidget
+    assert manus.docStats.minWordCount.text() == "7"
+    assert manus.docStats.minCharCount.text() == "31"
+
+    manus.docStats.toggleButton.toggle()
+    assert manus.docStats.mainStack.currentWidget() == manus.docStats.maxWidget
+    assert manus.docStats.maxTotalWords.text() == "7"
+    assert manus.docStats.maxTotalChars.text() == "31"
+
     # Toggle justify
     assert manus.docPreview.document().defaultTextOption().alignment() == Qt.AlignAbsolute
     manus.docPreview.setJustify(True)