Add characters_without_whitespace to the Text Analyzer

docs/tool-guide.md

@@ -7,7 +7,10 @@ MCP imports. Examples below show Python arguments; MCP uses the same parameter n
 
 `analyze_text("Hi hi!")` returns `characters=6`, `words=2`, `lines=1`,
 `sentences=1`, and `frequent_words=[{"word": "hi", "count": 2}]`.
-Characters include whitespace. Words are Unicode letter/digit sequences with
+Characters include
+whitespace; `characters_without_whitespace` counts every character for which
+`str.isspace()` is false, so punctuation and digits still count. Words are Unicode letter/digit
+sequences with
 optional internal apostrophes; underscores separate words. Frequency is case-insensitive,
 with ties ordered by first appearance. Lines follow `str.splitlines()`:
 empty input has zero lines and a final newline does not add an extra line.

src/mcp_tools_lab/tools/text.py

@@ -9,11 +9,16 @@ def analyze_text(text: str) -> dict:
 
     Words are letter/digit sequences (apostrophes within words are kept).
     Sentences are nonempty pieces separated by '.', '!', or '?'.
+    Characters exclude anything str.isspace() recognizes when counting
+    characters_without_whitespace.
     This is a simple heuristic, not linguistic analysis.
     """
     words = re.findall(r"[^\W_]+(?:['’][^\W_]+)*", text.lower())
     return {
         "characters": len(text),
+        "characters_without_whitespace": sum(
+            not character.isspace() for character in text
+        ),
         "words": len(words),
         "lines": len(text.splitlines()),
         "sentences": sum(bool(part.strip()) for part in re.split(r"[.!?]+", text)),

tests/test_text.py

@@ -2,7 +2,9 @@
 
 
 def test_empty_text():
-    assert analyze_text("") == {"characters": 0, "words": 0, "lines": 0,
+    assert analyze_text("") == {"characters": 0,
+                                "characters_without_whitespace": 0,
+                                "words": 0, "lines": 0,
                                 "sentences": 0, "frequent_words": []}
 
 
@@ -18,3 +20,22 @@ def test_unicode_and_trailing_newline():
     result = analyze_text("café café\n")
     assert result["words"] == 2
     assert result["lines"] == 1
+
+
+def test_characters_without_whitespace():
+    result = analyze_text("Hi there!\n")
+    assert result["characters"] == 10
+    assert result["characters_without_whitespace"] == 8
+
+
+def test_characters_without_whitespace_keeps_punctuation_and_digits():
+    result = analyze_text("a, 1\tb")
+    assert result["characters"] == 6
+    assert result["characters_without_whitespace"] == 4
+
+
+def test_characters_without_whitespace_whitespace_only():
+    result = analyze_text(" \t\r\n\u00a0")
+    assert result["characters"] == 5
+    assert result["characters_without_whitespace"] == 0
+    assert result["words"] == 0