Introduced hash valued location markers in the spec

tools/addlatexhash.dart

+// Copyright (c) 2014, the Dart project authors.  Please see the AUTHORS file
+// for details. All rights reserved. Use of this source code is governed by a
+// BSD-style license that can be found in the LICENSE file.
+//
+// ----------------------------------------------------------------------
+// This is a very specialized tool which was created in order to support
+// adding hash values used as location markers in the LaTeX source of the
+// language specification.  It is intended to be used as a filter from
+// the directory ../docs/language, in commands like the following:
+//
+//   dart ../../tools/addlatexhash.dart < dartLangSpec.tex >tmp.tex

[ricow1, 2014/10/14 06:09:12]

outdated comment, input and output is now taken as paramters

[eernst, 2014/10/14 15:53:25]

Done.

+//
+// This will yield a variant tmp.tex of the language specification with

[ricow1, 2014/10/14 06:09:11]

tmp.tex -> whatever you call the output file aboe

[eernst, 2014/10/14 15:53:25]

Done.

+// hash values filled in.  For more details, please check the language

[ricow1, 2014/10/14 06:09:12]

well, not yet, add a todo. Maybe also state that we remove the comments we can

[eernst, 2014/10/14 15:53:25]

Done.

+// specification source itself.
+//
+// NB: This utility assumes UN*X style line endings, \n; it will not
+// work with other styles.
+
+import 'dart:io';
+import 'dart:convert';
+import '../pkg/crypto/lib/crypto.dart';
+
+// ----------------------------------------------------------------------
+// Normalization of the text, i.e., removal or normalization
+// of elements that do not affect the output from latex
+
+// regexps

[ricow1, 2014/10/14 06:09:12]

obvious, remove comment

[eernst, 2014/10/14 15:53:24]

Done.

+
+final commentAllRe = new RegExp("^%");
+final commentRe = new RegExp("[^\\\\]%[^\\n]*");
+final whitespaceAllRe = new RegExp("^\\s+\$");
+final whitespaceLeadingRe = new RegExp("^\\s+[^\\n]");
+final whitespaceRe = new RegExp("[ \\t][ \\t]+");
+
+// normalization steps
+
+cutMatch(line, match, {startOffset:0, endOffset:0, glue:""}) {

[ricow1, 2014/10/14 06:09:12]

space after :

[eernst, 2014/10/14 15:53:24]

Done.

+  if (match == null) return line;
+  var start = match.start + startOffset;
+  var end = match.end + endOffset;
+  var len = line.length;
+  if (start < 0) start = 0;
+  if (end > len) end = len;
+  return line.substring(0, start) + glue + line.substring(end);
+}
+
+cutRegexp(line, re, {startOffset:0, endOffset:0, glue:""}) {

[ricow1, 2014/10/14 06:09:11]

space after :

[eernst, 2014/10/14 15:53:25]

Done.

+  return cutMatch(line, re.firstMatch(line),
+                  startOffset: startOffset,
+                  endOffset: endOffset,
+                   glue: glue);

[ricow1, 2014/10/14 06:09:11]

indentation

[ricow1, 2014/10/14 06:09:12]

indendtation

[eernst, 2014/10/14 15:53:25]

Done.

[eernst, 2014/10/14 15:53:25]

Done.

+}
+
+cutFromMatch(line, match, {offset:0, glue:""}) {

[ricow1, 2014/10/14 06:09:12]

space after :

[eernst, 2014/10/14 15:53:24]

Done.

+  if (match == null) return line;
+  return line.substring(0, match.start + offset) + glue;
+}
+
+cutFromRegexp(line, re, {offset:0, glue:""}) {

[ricow1, 2014/10/14 06:09:12]

space after :

[eernst, 2014/10/14 15:53:25]

Done.

+  return cutFromMatch(line, re.firstMatch(line), offset:offset, glue:glue);

[ricow1, 2014/10/14 06:09:12]

space after :

[eernst, 2014/10/14 15:53:25]

Done.

+}
+
+isWsOnly(line) => whitespaceAllRe.firstMatch(line) != null;
+isCommentOnly(line) => commentAllRe.firstMatch(line) != null;
+
+justEol(line) {
+  if (line.length == 0) return line;
+  return line[line.length-1] == '\n' ? "\n" : "";

[ricow1, 2014/10/14 06:09:11]

be consistent in using either ' or " for strings in the whole file
also, space around - in the array index calculation

[eernst, 2014/10/14 15:53:25]

Using '"' for strings, "'" for imports.

+}
+
+stripComment(line) {
+  // NB: it is tempting to remove everything from the '%' and out,
+  // including the final newline, if any, but this does not work.
+  // The problem is that TeX will do exactly this, but then it will
+  // add back a character that depends on its state (S, M, or N),
+  // and it is tricky to maintain a similar state that matches the
+  // state of TeX faithfully.  Hence, we remove the content of
+  // comments but do not remove the comments themselves, we just
+  // leave the '%' at the end of the line and let TeX manage its
+  // states in a way that does not differ from the file from before
+  // stripComment
+  if (isCommentOnly(line)) return "%\n";
+  return cutRegexp(line, commentRe, startOffset:2);

[ricow1, 2014/10/14 06:09:11]

space after :

[eernst, 2014/10/14 15:53:25]

Done.

+}
+
+// Reduce a wsOnly line to its eol, remove leading ws
+// entirely, and reduce multiple ws chars to one
+normalizeWhitespace(line) {
+  if (isWsOnly(line)) return justEol(line);
+  line = cutRegexp(line, whitespaceLeadingRe, endOffset:-1);

[ricow1, 2014/10/14 06:09:12]

space after :

[eernst, 2014/10/14 15:53:25]

Done.

+  var match;
+  while ((match = whitespaceRe.firstMatch(line)) != null) {
+    line = cutMatch(line, match, glue:" ");

[ricow1, 2014/10/14 06:09:12]

space after :

[eernst, 2014/10/14 15:53:25]

Done.

+  }
+  return line;
+}
+
+// Reduce sequences of >1 wsOnly lines to 1,
+// and sequences of >1 commentOnly lines to 1
+multilineNormalize(lines) {
+  var oldlines = lines;

[ricow1, 2014/10/14 06:09:11]

why are we doing this name mangling:
oldlines lines;
lines = new List();

We now reuse the input parameter, which is pretty strange

[eernst, 2014/10/14 15:53:25]

Was thinking "transforming lines several times" (where 'oldlines' would
repeatedly be the previous form, and 'lines' would accumulate the transformed
text).  Now using the slightly more functional style where the transformed text
gets a new name 'newLines'.

+  var afterBlankLines = false; // does 'line' succeed >0 empty lines?
+  var afterCommentLines = false; // .. succeed >0 commentOnly lines?
+  lines = new List();
+  for (var line in oldlines) {
+    if (afterBlankLines && afterCommentLines) {
+      // can never happen
+      throw "Bug, please report to eernst@";
+    } else if (afterBlankLines && !afterCommentLines) {
+      // at least one line before 'line' is wsOnly
+      if (!isWsOnly(line)) {
+        // blank line block ended
+        afterCommentLines = isCommentOnly(line);
+        // special case: it seems to be safe to remove commentOnly lines
+        // after wsOnly lines, so the TeX state must be predictably right;
+        // next line will then be afterCommentLines and be dropped, so
+        // we drop the entire comment block---which is very useful; we can
+        // also consider this comment line to be an empty line, such that
+        // subsequent empty lines can be considered to be in a block of
+        // empty lines; note that almost all variants of this will break..
+        if (afterCommentLines) {
+          // _current_ 'line' a commentOnly here
+          afterBlankLines = true;
+          afterCommentLines = false;
+          // and do not add 'line'
+        } else {
+          // after blanks, but current 'line' is neither blank nor comment
+          afterBlankLines = false;
+          lines.add(line);
+        }
+      } else {
+        // blank line block continues, do not add 'line'

[ricow1, 2014/10/14 06:09:12]

do we really want an else clause that does nothing

[eernst, 2014/10/14 15:53:25]

Worried about performance?  Not sure about the costs.  Where else would you put
an invariant that justifies leaving this case as a noop (rather than just a
forgotten case)?

[ricow1, 2014/10/15 08:29:05]

I would just have it as a comment, but this is fine, just leave it

+      }
+    } else if (!afterBlankLines && afterCommentLines) {
+      // at least one line before 'line' is commentOnly
+      if (!isCommentOnly(line)) {
+        // comment line block ended
+        afterBlankLines = isWsOnly(line);
+        afterCommentLines = false;
+        lines.add(line);
+      } else {
+        // comment line block continues, do not add 'line'

[ricow1, 2014/10/14 06:09:12]

same as above

[eernst, 2014/10/14 15:53:25]

Same issue, to be resolved together.

+      }
+    } else /* !afterBlankLines && !afterCommentLines */ {

[ricow1, 2014/10/14 06:09:12]

you have comments after the line in all other places in this file, also do that
here

[eernst, 2014/10/14 15:53:25]

This is actually a bit different, because this comment contains the exact code
that would have occurred here if I had used a style where all cases are spelled
out (and hence exactly one of them applies at runtime).  But maybe the best
treatment of this situation is actually to make it real code, in an assertion,
such that we catch situations where the other cases are edited, or null is
encountered, etc.  Did that.

[ricow1, 2014/10/15 08:29:05]

Acknowledged.

+      // no wsOnly or commentOnly lines preceed 'line'
+      if (isWsOnly(line)) afterBlankLines = true;
+      if (isCommentOnly(line)) afterCommentLines = true;
+      if (!afterCommentLines) lines.add(line);
+      // else skipping commentOnly line after nonWs, nonComment text
+    }
+  }
+  return lines;
+}
+
+// select the elements in the pipeline
+
+normalize(line) => normalizeWhitespace(stripComment(line));
+
+sispNormalize(line) => stripComment(line);
+
+// ----------------------------------------------------------------------
+// Managing fragments with significant spacing
+
+final dartCodeBeginRe = new RegExp("^\\s*\\\\begin{dartCode}");
+final dartCodeEndRe = new RegExp ("^\\s*\\\\end{dartCode}");
+
+sispIs(line, targetRe) {
+  return targetRe.firstMatch(line) != null;
+}
+
+sispIsDartBegin(line) => sispIs(line, dartCodeBeginRe);
+sispIsDartEnd(line) => sispIs(line, dartCodeEndRe);
+
+// ----------------------------------------------------------------------
+// main

[ricow1, 2014/10/14 06:09:12]

obvious, remove comment

[eernst, 2014/10/14 15:53:24]

It wasn't really meant to be unobvious, it should make the file as a whole more
navigable, because of "section" dividers like the line here.  Don't we use any
such thing?

[ricow1, 2014/10/15 08:29:05]

I never do, if I want to structure something together logically, I will put it
in a class. The problem with doing it like this is that over time people will
add code in sections where it does not belong, the comments will be
outdated/wrong, and people don use a comment syntax so it is hard to do anything
with command line wise. If the code is self explanatory I never add a comment.
There are a few cases where section headers like this make sense, e.g., if you
have code that is preprocessed before compilation

+
+main ([args]) {
+  if (args.length != 2) {
+    print("Usage: addlatexhash.dart <input-file> <output-file>");
+    throw "Received ${args.length} arguments, expected two";
+  }
+
+  var inputFile = new File(args[0]);
+  var outputFile = new File(args[1]);
+  assert(inputFile.existsSync());
+
+  var lines = inputFile.readAsLinesSync();
+  // single-line normalization
+  var inDartCode = false;
+  var newLines = new List();
+
+  for (var line in lines) {
+    if (sispIsDartBegin(line)) {
+      inDartCode = true;
+    } else if (sispIsDartEnd(line)) {
+      inDartCode = false;
+    }
+    if (inDartCode) {
+      newLines.add(sispNormalize(line + "\n"));

[ricow1, 2014/10/14 06:09:12]

maybe remove the "\n" here and join on it when writing the output file

[eernst, 2014/10/14 15:53:24]

Would look better, but I would need to change many other parts of the algorithm,
because lines with an eol char have a different effect than lines without an eol
char (TeX and LaTeX are very peculiar with newlines).

[ricow1, 2014/10/15 08:29:05]

Acknowledged.

+    } else {
+      newLines.add(normalize(line + "\n"));
+    }
+  }
+
+  // multi-line normalization
+  newLines = multilineNormalize(newLines);
+
+  // output result
+  outputFile.writeAsStringSync(newLines.join());
+}