Fix word counter for align and indent tags

nw/core/index.py

@@ -908,6 +908,9 @@ def countWords(theText):
     paraCount = 0
     prevEmpty = True
 
+    if not isinstance(theText, str):
+        return charCount, wordCount, paraCount
+
     # We need to treat dashes as word separators for counting words.
     # The check+replace apprach is much faster that direct replace for
     # large texts, and a bit slower for small texts, but in the latter
@@ -920,33 +923,38 @@ def countWords(theText):
     for aLine in theText.splitlines():
 
         countPara = True
-        theLen    = len(aLine)
 
-        if theLen == 0:
+        if not aLine:
             prevEmpty = True
             continue
         if aLine[0] == "@" or aLine[0] == "%":
             continue
 
-        if aLine[0:5] == "#### ":
+        if aLine[0] == "#":
-            wordCount -= 1
+            if aLine[:5] == "#### ":
-            charCount -= 5
+                aLine = aLine[5:]
-            countPara = False
+                countPara = False
-        elif aLine[0:4] == "### ":
+            elif aLine[:4] == "### ":
-            wordCount -= 1
+                aLine = aLine[4:]
-            charCount -= 4
+                countPara = False
-            countPara = False
+            elif aLine[:3] == "## ":
-        elif aLine[0:3] == "## ":
+                aLine = aLine[3:]
-            wordCount -= 1
+                countPara = False
-            charCount -= 3
+            elif aLine[:2] == "# ":
-            countPara = False
+                aLine = aLine[2:]
-        elif aLine[0:2] == "# ":
+                countPara = False
-            wordCount -= 1
+        elif aLine[0] == ">" or aLine[-1] == "<":
-            charCount -= 2
+            if aLine[:2] == ">>":
-            countPara = False
+                aLine = aLine[2:].lstrip(" ")
+            elif aLine[:1] == ">":
+                aLine = aLine[1:].lstrip(" ")
+            if aLine[-2:] == "<<":
+                aLine = aLine[:-2].rstrip(" ")
+            elif aLine[-1:] == "<":
+                aLine = aLine[:-1].rstrip(" ")
 
         wordCount += len(aLine.split())
-        charCount += theLen
+        charCount += len(aLine)
         if countPara and prevEmpty:
             paraCount += 1
 

sample/nwProject.nwx

@@ -1,13 +1,13 @@
 <?xml version='1.0' encoding='utf-8'?>
-<novelWriterXML appVersion="1.4a0" hexVersion="0x010400a0" fileVersion="1.2" timeStamp="2021-06-10 14:15:49">
+<novelWriterXML appVersion="1.4a0" hexVersion="0x010400a0" fileVersion="1.2" timeStamp="2021-06-10 23:37:32">
   <project>
     <name>Sample Project</name>
     <title>Sample Project</title>
     <author>Jane Smith</author>
     <author>Jay Doh</author>
-    <saveCount>1095</saveCount>
+    <saveCount>1096</saveCount>
     <autoCount>188</autoCount>
-    <editTime>52304</editTime>
+    <editTime>52328</editTime>
   </project>
   <settings>
     <doBackup>False</doBackup>
@@ -17,8 +17,8 @@
     <autoOutline>True</autoOutline>
     <lastEdited>636b6aa9b697b</lastEdited>
     <lastViewed>636b6aa9b697b</lastViewed>
-    <lastWordCount>1224</lastWordCount>
+    <lastWordCount>1217</lastWordCount>
-    <novelWordCount>848</novelWordCount>
+    <novelWordCount>841</novelWordCount>
     <notesWordCount>376</notesWordCount>
     <autoReplace>
       <entry key="A">B</entry>
@@ -63,8 +63,8 @@
       <status>Started</status>
       <exported>True</exported>
       <layout>TITLE</layout>
-      <charCount>244</charCount>
+      <charCount>241</charCount>
-      <wordCount>43</wordCount>
+      <wordCount>42</wordCount>
       <paraCount>3</paraCount>
       <cursorPos>252</cursorPos>
     </item>
@@ -118,8 +118,8 @@
       <status>1st Draft</status>
       <exported>True</exported>
       <layout>SCENE</layout>
-      <charCount>2450</charCount>
+      <charCount>2434</charCount>
-      <wordCount>439</wordCount>
+      <wordCount>433</wordCount>
       <paraCount>14</paraCount>
       <cursorPos>61</cursorPos>
     </item>

tests/test_core/test_core_index.py

@@ -1177,29 +1177,59 @@ def testCoreIndex_CheckTextCounts(dummyGUI):
 def testCoreIndex_CountWords():
     """Test the word counter and the exclusion filers.
     """
-    testText = (
+    # Non-Text
+    assert countWords(None) == (0, 0, 0)
+    assert countWords(1234) == (0, 0, 0)
+
+    # General Text
+    cC, wC, pC = countWords((
         "# Heading One\n"
         "## Heading Two\n"
         "### Heading Three\n"
-        "#### Heading Four\n"
+        "#### Heading Four\n\n"
-        "\n"
+        "@tag: value\n\n"
-        "@tag: value\n"
+        "% A comment that should not be counted.\n\n"
-        "\n"
+        "The first paragraph.\n\n"
-        "% A comment that should n ot be counted.\n"
+        "The second paragraph.\n\n\n"
-        "\n"
+        "The third paragraph.\n\n"
-        "The first paragraph.\n"
-        "\n"
-        "The second paragraph.\n"
-        "\n"
-        "\n"
-        "The third paragraph.\n"
-        "\n"
         "Dashes\u2013and even longer\u2014dashes."
-    )
+    ))
-    cC, wC, pC = countWords(testText)
-
     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
+
 # END Test testCoreIndex_CountWords