Checks more rules

.gitignore

@@ -20,6 +20,7 @@
 
 # Top-level jar, but not jars in subfolders (if any)
 *.jar
+*.zip
 !*/*.jar
 
 # File generated by the JaCoCo code coverage tool

Rules.md

@@ -0,0 +1,41 @@
+Rules checked by TeXtidote
+==========================
+
+Style
+-----
+
+- A section title should start with a capital letter. [sh:001]
+- A section title should not end with a punctuation symbol. [sh:002]
+- A section title should not be written in all caps. The LaTeX stylesheet
+  takes care of rendering titles in caps if needed. [sh:003]
+- A figure caption should end with a period. [sh:004]
+
+Citations and references
+------------------------
+
+- There should be one space before a \cite or \ref command [sh:c:001], and
+  no space after [sh:c:002].
+
+Figures
+-------
+- Every figure should have a label, and every figure should be referenced at
+  least once in the text. [sh:figref]
+- Figures should not refer to hard-coded local paths. [sh:relpath]
+
+Typesetting
+-----------
+
+- You should not break lines manually in a paragraph. Either start a new
+  paragraph or stay in the current one. [sh:nobreak]
+
+Structure
+---------
+
+- A section should not contain a single sub-section. More generally, a division
+  of level n should not contain a single division of level n+1. [sh:nsubdiv]
+
+Potentially suspicious
+----------------------
+
+- There should be at least N words between two section headings (currently
+  N=50). [sh:seclen]

Source/Core/src/ca/uqac/lif/textidote/Detexer.java

@@ -156,7 +156,7 @@ protected AnnotatedString removeAllMarkup(AnnotatedString as)
 	protected AnnotatedString removeMarkup(AnnotatedString as_out, int line_pos)
 	{
 		// Common environments
-		as_out = as_out.replaceAll("\\\\(begin|end)\\{(itemize|enumerate|document|thm|abstract|eqnarray|compactitem|query|center|minipage)\\}", "");
+		as_out = as_out.replaceAll("\\\\(begin|end)\\{(itemize|enumerate|inparaenum|document|thm|abstract|eqnarray|compactitem|query|center|minipage)\\}", "");
 		// List items
 		as_out = as_out.replaceAll("\\\\item\\s*", "");
 		// Images
@@ -166,7 +166,7 @@ protected AnnotatedString removeMarkup(AnnotatedString as_out, int line_pos)
 		// Footnotes (ignore)
 		as_out = as_out.replaceAll("\\\\footnote\\{.*?\\}", "");
 		// Replace citations by dummy placeholder
-		as_out = as_out.replaceAll("\\\\(cite|citep|citel)\\{.*?\\}", "[0]");
+		as_out = as_out.replaceAll("\\\\(cite|citep|citel)(\\[.*?\\])*\\{.*?\\}", "[0]");
 		// Replace verbatim by dummy placeholder
 		as_out = as_out.replaceAll("\\\\verb\\+[^\\+]*?\\+", "[0]");
 		// Replace references and URLs by dummy placeholder

Source/Core/src/ca/uqac/lif/textidote/Main.java

@@ -37,6 +37,9 @@
 import ca.uqac.lif.textidote.rules.CheckFigurePaths;
 import ca.uqac.lif.textidote.rules.CheckFigureReferences;
 import ca.uqac.lif.textidote.rules.CheckLanguage;
+import ca.uqac.lif.textidote.rules.CheckNoBreak;
+import ca.uqac.lif.textidote.rules.CheckSubsectionSize;
+import ca.uqac.lif.textidote.rules.CheckSubsections;
 import ca.uqac.lif.textidote.rules.LanguageFactory;
 import ca.uqac.lif.textidote.rules.RegexRule;
 import ca.uqac.lif.util.AnsiPrinter;
@@ -214,7 +217,7 @@ public static void main(String[] args) throws IOException
 		{
 			System.err.println("No filename is specified");
 			System.err.println("");
-			cli_parser.printHelp("Usage: java -jar TeXtidote.jar [options] file1 [file2 ...]", System.err);
+			cli_parser.printHelp("Usage: java -jar textidote.jar [options] file1 [file2 ...]", System.err);
 			System.exit(1);
 		}
 		AnnotatedString last_string = null;
@@ -298,6 +301,9 @@ protected static void populateRules(Linter linter)
 		linter.addDetexed(readRules(REGEX_FILENAME_DETEX));
 		linter.add(new CheckFigureReferences());
 		linter.add(new CheckFigurePaths());
+		linter.add(new CheckSubsections());
+		linter.add(new CheckSubsectionSize());
+		linter.add(new CheckNoBreak());
 	}
 
 	protected static List<Rule> readRules(String filename)

Source/Core/src/ca/uqac/lif/textidote/as/AnnotatedString.java

@@ -559,7 +559,14 @@ public Match find(/* @non_null @*/ String regex)
 		}
 		for (int i = 1; i < m.groupCount(); i++)
 		{
-			to = to.replace("$" + i, m.group(i));
+			if (m.group(i) != null)
+			{
+				to = to.replace("$" + i, m.group(i));
+			}
+			else
+			{
+				to = to.replace("$" + i, "");
+			}
 		}
 		part_left.append(to);
 		AnnotatedString part_right = substring(new Position(found_pos.getLine(), found_pos.getColumn() + m.getMatch().length()));
@@ -576,19 +583,19 @@ public Match find(/* @non_null @*/ String regex)
 	{
 		int max_iterations = 1000;
 		AnnotatedString replaced = this;
+		Position last_pos = Position.ZERO;
 		for (int i = 0; i < max_iterations; i++)
 		{
-			AnnotatedString rep = replaced.replace(regex, to);
-			if (rep.toString().compareTo(replaced.toString()) != 0)
-			{
-				// Something changed
-				replaced = rep;
-			}
-			else
+			Match m = replaced.find(regex, last_pos);
+			if (m == null)
 			{
-				// No change: stop
+				// No cigarettes, no matches
 				break;
 			}
+			Position new_pos = m.getPosition();
+			AnnotatedString rep = replaced.replace(regex, to, last_pos);
+			replaced = rep;
+			last_pos = new_pos.moveBy(1);
 		}
 		return replaced;
 	}

Source/Core/src/ca/uqac/lif/textidote/render/postamble.html

@@ -1,5 +1,5 @@
 <hr/>
 Output produced by TeXtidote, &copy; 2018 Sylvain Hall&eacute; - All rights reserved.<br/>
-See the <a href="https://github.com/sylvainhalle/texlint">TeXLint website</a> for more information.
+See the <a href="https://sylvainhalle.github.io/sylvainhalle/textidote">TeXtidote website</a> for more information.
 </body>
 </html>

Source/Core/src/ca/uqac/lif/textidote/render/preamble.html

@@ -11,7 +11,8 @@
   padding: 2pt;
   border-radius: 4pt;
   cursor: help;
-  opacity: 0.8;
+  opacity: 0.7;
+  border: dashed 1px;
 }
 .highlight {
   background-color: red;
@@ -54,5 +55,5 @@
 </style>
 </head>
 <body>
-<h1 class="textidote"><span class="no-text">Results of TeXtidote analysis</span></h1>
+<a href="https://sylvainhalle.github.io/textidote"><h1 class="textidote"><span class="no-text">Results of TeXtidote analysis</span></h1></a>
 <p>Here is the result of analyzing your LaTeX file with TeXtidote.</p>

Source/Core/src/ca/uqac/lif/textidote/rules/CheckFigureReferences.java

@@ -61,18 +61,28 @@ public List<Advice> evaluate(AnnotatedString s, AnnotatedString original)
 		boolean in_figure = false;
 		Map<String,Position> figure_defs = new HashMap<String,Position>();
 		List<String> lines = s.getLines();
+		boolean found_label = false;
 		// Step 1: find all figure labels
 		for (int line_cnt = 0; line_cnt < lines.size(); line_cnt++)
 		{
 			String line = lines.get(line_cnt);
 			if (line.matches(".*\\\\begin\\s*\\{\\s*figure.*"))
 			{
 				in_figure = true;
+				found_label = false;
 				continue;
 			}
 			if (line.matches(".*\\\\end\\s*\\{\\s*figure.*"))
 			{
 				in_figure = false;
+				if (!found_label)
+				{
+					// This figure is missing a label
+					Position start_pos = s.getSourcePosition(new Position(line_cnt, 0));
+					Position end_pos = start_pos.moveBy(1);
+					Range r = new Range(start_pos, end_pos);
+					out_list.add(new Advice(this, r, "This figure is missing a label", original.getResourceName(), original.getLine(start_pos.getLine())));	
+				}
 				continue;
 			}
 			if (in_figure)
@@ -83,14 +93,7 @@ public List<Advice> evaluate(AnnotatedString s, AnnotatedString original)
 					String fig_name = mat.group(1).trim();
 					Position fig_pos = s.getSourcePosition(new Position(line_cnt, mat.start(1)));
 					figure_defs.put(fig_name, fig_pos);
-				}
-				else
-				{
-					// This figure is missing a label
-					Position start_pos = s.getSourcePosition(new Position(line_cnt, 0));
-					Position end_pos = start_pos.moveBy(1);
-					Range r = new Range(start_pos, end_pos);
-					out_list.add(new Advice(this, r, "This figure is missing a label", original.getResourceName(), original.getLine(start_pos.getLine())));	
+					found_label = true;
 				}
 			}
 		}

Source/Core/src/ca/uqac/lif/textidote/rules/CheckLanguage.java

@@ -58,7 +58,14 @@ public class CheckLanguage extends Rule
 	 * that LaTeX ignores multiple spaces anyway, it is advisable to
 	 *  turn it off.
 	 */
-	protected boolean m_disableWhitespace = true; 
+	protected boolean m_disableWhitespace = true;
+
+	/**
+	 * Whether to disable Language Tool's "unpaired symbol" rule. The detexing
+	 * of the string leaves a few unmatched "}", so we just ignore this rule
+	 * when it concerns this particular character.
+	 */
+	protected boolean m_disableUnpaired = true;
 
 	/**
 	 * Creates a new rule for checking a specific language
@@ -153,6 +160,15 @@ public List<Advice> evaluate(AnnotatedString s, AnnotatedString original)
 					r = new Range(start_src_pos, end_src_pos);
 				}
 			}
+			// Exception for the disable unpaired rule
+			if (m_disableUnpaired && rm.getRule().getId().startsWith("EN_UNPAIRED_BRACKETS"))
+			{
+				if (rm.getMessage().contains("{"))
+				{
+					// We ignore the unpaired symbol for this character
+					continue;
+				}
+			}
 			// Exception if spelling mistake and a dictionary is provided
 			String clean_line = s.getLine(start_pos.getLine());
 			int end_p = end_pos.getColumn();

Source/Core/src/ca/uqac/lif/textidote/rules/CheckNoBreak.java

@@ -0,0 +1,81 @@
+/*
+    TeXtidote, a linter for LaTeX documents
+    Copyright (C) 2018  Sylvain Hallé
+
+    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/>.
+ */
+package ca.uqac.lif.textidote.rules;
+
+import java.util.ArrayList;
+import java.util.List;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+import ca.uqac.lif.textidote.Advice;
+import ca.uqac.lif.textidote.Rule;
+import ca.uqac.lif.textidote.as.AnnotatedString;
+import ca.uqac.lif.textidote.as.Position;
+import ca.uqac.lif.textidote.as.Range;
+
+/**
+ * Checks that text paragraphs do not contain forced line breaks.
+ * 
+ * @author Sylvain Hallé
+ *
+ */
+public class CheckNoBreak extends Rule 
+{
+	/**
+	 * The pattern for finding figure labels
+	 */
+	Pattern m_breakPattern = Pattern.compile("\\\\\\\\");
+
+	public CheckNoBreak()
+	{
+		super("sh:nobreak");
+	}
+
+	@Override
+	public List<Advice> evaluate(AnnotatedString s, AnnotatedString original)
+	{
+		List<Advice> out_list = new ArrayList<Advice>();
+		List<String> lines = s.getLines();
+		int env_level = 0;
+		for (int line_cnt = 0; line_cnt < lines.size(); line_cnt++)
+		{
+			String line = lines.get(line_cnt);
+			if (line.matches(".*\\\\begin\\s*\\{\\s*(equation|table|tabular|verbatim|lstlisting|IEEEkeywords|figure).*") || line.matches(".*\\\\\\[.*"))
+			{
+				env_level++;
+			}
+			if (env_level == 0)
+			{
+				Matcher mat = m_breakPattern.matcher(line);
+				if (mat.find())
+				{
+					// Forced break
+					Position start_pos = s.getSourcePosition(new Position(line_cnt, mat.start()));
+					Position end_pos = s.getSourcePosition(new Position(line_cnt, mat.start() + mat.group(0).length()));
+					Range r = new Range(start_pos, end_pos);
+					out_list.add(new Advice(this, r, "You should not break lines manually in a paragraph. Either start a new paragraph or stay in the current one.", original.getResourceName(), original.getLine(start_pos.getLine())));	
+				}
+			}
+			if (line.matches(".*\\\\end\\s*\\{\\s*(equation|table|tabular|verbatim|lstlisting|IEEEkeywords|figure).*") || line.matches(".*\\\\\\].*"))
+			{
+				env_level--;
+			}
+		}
+		return out_list;
+	}
+}