Code Cleanup

- Relocated the Table::getCharLength() from Johannes to text.cpp/characters()
  because it is a general-purpose function, and will be the start of the UTF8
  conversion of all text.cpp code.
- Added unit tests for characters().

src/Table.cpp

@@ -108,7 +108,7 @@ void Table::setTableDashedUnderline ()
 int Table::addColumn (const std::string& col)
 {
   mSpecifiedWidth.push_back (minimum);
-  mMaxDataWidth.push_back (col == "" ? 1 : getCharLength (col));
+  mMaxDataWidth.push_back (col == "" ? 1 : characters (col));
   mCalculatedWidth.push_back (0);
   mColumnPadding.push_back (0);
 
@@ -193,11 +193,11 @@ void Table::addCell (const int row, const int col, const std::string& data)
     std::vector <std::string> lines;
     split (lines, data, "\n");
     for (unsigned int i = 0; i < lines.size (); ++i)
-      if (getCharLength (lines[i]) > length)
-        length = getCharLength (lines[i]);
+      if (characters (lines[i]) > length)
+        length = characters (lines[i]);
   }
   else
-    length = getCharLength (data);
+    length = characters (data);
 
   // Automatically maintain max width.
   mMaxDataWidth[col] = max (mMaxDataWidth[col], length);
@@ -435,25 +435,6 @@ Table::just Table::getHeaderJustification (int col)
        : left;
 }
 
-////////////////////////////////////////////////////////////////////////////////
-int Table::getCharLength (const std::string& str)
-{
-	int byteLength = str.length ();
-	int charLength = byteLength;
-	const char* data = str.data ();
-
-	// decrement the number of bytes for each byte that matches 0b10??????
-	// this way only the first byte of any utf8 sequence is counted
-	for (int i = 0; i < byteLength; i++)
-  {
-		// extract the two MSB and check whether they are 10
-		if ((data[i] & 0xC0) == 0x80)
-			charLength--;
-	}
-
-	return charLength;
-}
-
 ////////////////////////////////////////////////////////////////////////////////
 // data            One    Data to be rendered
 // width           8      Max data width for column/specified width
@@ -478,7 +459,7 @@ const std::string Table::formatHeader (
 
   std::string data = mColumns[col];
   Color c = getHeaderUnderline (col);
-  int gap = width - strippedLength (data);  // TODO Does this need Table::getCharLength too?
+  int gap = width - strippedLength (data);  // TODO Does this need characters () too?
 
   std::string pad = std::string (padding, ' ');
 
@@ -561,7 +542,7 @@ void Table::formatCell (
   for (size_t chunk = 0; chunk < chunks.size (); ++chunk)
   {
     // Place the data within the available space - justify.
-    int gap = width - getCharLength (chunks[chunk]);
+    int gap = width - characters (chunks[chunk]);
 
     preJust = "";
     postJust = "";

src/Table.h

@@ -100,7 +100,6 @@ private:
            void calculateColumnWidths ();
            just getJustification (const int, const int);
            just getHeaderJustification (const int);
-           int getCharLength (const std::string&);
            const std::string formatHeader (const int, const int, const int);
            const std::string formatHeaderDashedUnderline (const int, const int, const int);
            void formatCell (const int, const int, const int, const int, const int, std::vector <std::string>&, std::string&);

src/tests/text.t.cpp

@@ -34,7 +34,7 @@ Context context;
 ////////////////////////////////////////////////////////////////////////////////
 int main (int argc, char** argv)
 {
-  UnitTest t (191);
+  UnitTest t (194);
 
   // void wrapText (std::vector <std::string>& lines, const std::string& text, const int width)
   std::string text = "This is a test of the line wrapping code.";
@@ -387,6 +387,11 @@ int main (int argc, char** argv)
   t.is (strippedLength (std::string ("\033[0m")),                           0, "strippedLength ^[[0m                        -> 0");
   t.is (strippedLength (std::string ("\033[1m\033[0m")),                    0, "strippedLength ^[[1m^[[0m                   -> 0");
 
+  // int characters (const std::string&);
+  t.is (characters ("Çirçös"),            6, "characters (Çirçös) == 6");
+  t.is (characters ("ツネナラム"),        5, "characters (ツネナラム) == 6");
+  t.is (characters ("Zwölf Boxkämpfer"), 16, "characters (Zwölf Boxkämpfer) == 6");
+
   return 0;
 }
 

src/text.cpp

@@ -620,3 +620,22 @@ int strippedLength (const std::string& input)
 }
 
 ////////////////////////////////////////////////////////////////////////////////
+int characters (const std::string& str)
+{
+  int byteLength = str.length ();
+  int charLength = byteLength;
+  const char* data = str.data ();
+
+  // decrement the number of bytes for each byte that matches 0b10??????
+  // this way only the first byte of any utf8 sequence is counted
+  for (int i = 0; i < byteLength; i++)
+  {
+    // extract the two MSB and check whether they are 10
+    if ((data[i] & 0xC0) == 0x80)
+      charLength--;
+  }
+
+  return charLength;
+}
+
+////////////////////////////////////////////////////////////////////////////////

src/text.h

@@ -31,7 +31,7 @@
 #include <vector>
 #include "../auto.h"
 
-// text.cpp
+// text.cpp, Non-UTF-8 aware.
 void wrapText (std::vector <std::string>&, const std::string&, const int);
 std::string trimLeft (const std::string& in, const std::string& t = " ");
 std::string trimRight (const std::string& in, const std::string& t = " ");
@@ -60,5 +60,8 @@ std::string::size_type find (const std::string&, const std::string&, bool sensit
 std::string::size_type find (const std::string&, const std::string&, std::string::size_type, bool sensitive = true);
 int strippedLength (const std::string&);
 
+// UTF-8 aware.
+int characters (const std::string&);
+
 #endif
 ////////////////////////////////////////////////////////////////////////////////