Add style mapping for all caps

10 files changed, 93 insertions, 38 deletions

diff --git a/NEWS b/NEWS
index 30178ae..28e58e8 100644
--- a/NEWS
+++ b/NEWS
@@ -1,3 +1,7 @@
+# 1.4.14
+
+* Add style mapping for all caps.
+
 # 1.4.13
 
 * Use package-lock.json instead of npm-shrinkwrap.json.
diff --git a/README.md b/README.md
index 2185b22..6aa6a55 100644
--- a/README.md
+++ b/README.md
@@ -726,6 +726,17 @@ strike
 Note that this matches text that has had strikethrough explicitly applied to it.
 It will not match any text that is struckthrough because of its paragraph or run style.
 
+#### All caps
+
+Match explicitly all caps text:
+
+```
+all-caps
+```
+
+Note that this matches text that has had all caps explicitly applied to it.
+It will not match any text that is all caps because of its paragraph or run style.
+
 #### Small caps
 
 Match explicitly small caps text:
diff --git a/lib/document-to-html.js b/lib/document-to-html.js
index 2267933..32e8b03 100644
--- a/lib/document-to-html.js
+++ b/lib/document-to-html.js
@@ -130,6 +130,9 @@ function DocumentConversion(options, comments) {
         if (run.isSmallCaps) {
             paths.push(findHtmlPathForRunProperty("smallCaps"));
         }
+        if (run.isAllCaps) {
+            paths.push(findHtmlPathForRunProperty("allCaps"));
+        }
         if (run.isStrikethrough) {
             paths.push(findHtmlPathForRunProperty("strikethrough", "s"));
         }
diff --git a/lib/documents.js b/lib/documents.js
index df48beb..edc9b7c 100644
--- a/lib/documents.js
+++ b/lib/documents.js
@@ -59,6 +59,7 @@ function Run(children, properties) {
         isUnderline: properties.isUnderline,
         isItalic: properties.isItalic,
         isStrikethrough: properties.isStrikethrough,
+        isAllCaps: properties.isAllCaps,
         isSmallCaps: properties.isSmallCaps,
         verticalAlignment: properties.verticalAlignment || verticalAlignment.baseline,
         font: properties.font || null,
diff --git a/lib/docx/body-reader.js b/lib/docx/body-reader.js
index ad4f409..77f194b 100644
--- a/lib/docx/body-reader.js
+++ b/lib/docx/body-reader.js
@@ -73,6 +73,7 @@ function BodyReader(options) {
                 isUnderline: readUnderline(element.first("w:u")),
                 isItalic: readBooleanElement(element.first("w:i")),
                 isStrikethrough: readBooleanElement(element.first("w:strike")),
+                isAllCaps: readBooleanElement(element.first("w:caps")),
                 isSmallCaps: readBooleanElement(element.first("w:smallCaps"))
             };
         });
diff --git a/lib/style-reader.js b/lib/style-reader.js
index f686b28..07521ad 100644
--- a/lib/style-reader.js
+++ b/lib/style-reader.js
@@ -39,7 +39,7 @@ function readDocumentMatcher(string) {
 
 function documentMatcherRule() {
     var sequence = lop.rules.sequence;
-    
+
     var identifierToConstant = function(identifier, constant) {
         return lop.rules.then(
             lop.rules.token("identifier", identifier),
@@ -48,15 +48,15 @@ function documentMatcherRule() {
             }
         );
     };
-    
+
     var paragraphRule = identifierToConstant("p", documentMatchers.paragraph);
     var runRule = identifierToConstant("r", documentMatchers.run);
-    
+
     var elementTypeRule = lop.rules.firstOf("p or r or table",
         paragraphRule,
         runRule
     );
-    
+
     var styleIdRule = lop.rules.then(
         classRule,
         function(styleId) {
@@ -86,7 +86,7 @@ function documentMatcherRule() {
             }
         )
     );
-    
+
     var styleNameRule = lop.rules.sequence(
         lop.rules.tokenOfType("open-square-bracket"),
         lop.rules.sequence.cut(),
@@ -95,7 +95,7 @@ function documentMatcherRule() {
         lop.rules.tokenOfType("close-square-bracket")
     ).head();
 
-    
+
     var listTypeRule = lop.rules.firstOf("list type",
         identifierToConstant("ordered-list", {isOrdered: true}),
         identifierToConstant("unordered-list", {isOrdered: false})
@@ -130,7 +130,7 @@ function documentMatcherRule() {
             return matcherOptions;
         });
     }
-    
+
     var paragraphOrRun = sequence(
         sequence.capture(elementTypeRule),
         sequence.capture(createMatcherSuffixesRule([
@@ -141,7 +141,7 @@ function documentMatcherRule() {
     ).map(function(createMatcher, matcherOptions) {
         return createMatcher(matcherOptions);
     });
-    
+
     var table = sequence(
         lop.rules.token("identifier", "table"),
         sequence.capture(createMatcherSuffixesRule([
@@ -156,9 +156,10 @@ function documentMatcherRule() {
     var italic = identifierToConstant("i", documentMatchers.italic);
     var underline = identifierToConstant("u", documentMatchers.underline);
     var strikethrough = identifierToConstant("strike", documentMatchers.strikethrough);
+    var allCaps = identifierToConstant("all-caps", documentMatchers.allCaps);
     var smallCaps = identifierToConstant("small-caps", documentMatchers.smallCaps);
     var commentReference = identifierToConstant("comment-reference", documentMatchers.commentReference);
-    
+
     var breakMatcher = sequence(
         lop.rules.token("identifier", "br"),
         sequence.cut(),
@@ -187,6 +188,7 @@ function documentMatcherRule() {
         italic,
         underline,
         strikethrough,
+        allCaps,
         smallCaps,
         commentReference,
         breakMatcher
@@ -211,7 +213,7 @@ function htmlPathRule() {
             }).valueOrElse(false);
         }
     );
-    
+
     var separatorRule = lop.rules.then(
         lop.rules.optional(lop.rules.sequence(
             lop.rules.tokenOfType("colon"),
@@ -229,7 +231,7 @@ function htmlPathRule() {
         identifierRule,
         lop.rules.tokenOfType("choice")
     );
-    
+
     var styleElementRule = lop.rules.sequence(
         capture(tagNamesRule),
         capture(lop.rules.zeroOrMore(classRule)),
@@ -249,7 +251,7 @@ function htmlPathRule() {
         }
         return htmlPaths.element(tagName, attributes, options);
     });
-    
+
     return lop.rules.firstOf("html path",
         lop.rules.then(lop.rules.tokenOfType("bang"), function() {
             return htmlPaths.ignore;
@@ -267,7 +269,7 @@ function htmlPathRule() {
         )
     );
 }
-    
+
 var identifierRule = lop.rules.then(
     lop.rules.tokenOfType("identifier"),
     decodeEscapeSequences
diff --git a/lib/styles/document-matchers.js b/lib/styles/document-matchers.js
index 11b577f..005e2db 100644
--- a/lib/styles/document-matchers.js
+++ b/lib/styles/document-matchers.js
@@ -5,6 +5,7 @@ exports.bold = new Matcher("bold");
 exports.italic = new Matcher("italic");
 exports.underline = new Matcher("underline");
 exports.strikethrough = new Matcher("strikethrough");
+exports.allCaps = new Matcher("allCaps");
 exports.smallCaps = new Matcher("smallCaps");
 exports.commentReference = new Matcher("commentReference");
 exports.lineBreak = new Matcher("break", {breakType: "line"});
diff --git a/test/document-to-html.tests.js b/test/document-to-html.tests.js
index 6e61d45..4283e86 100644
--- a/test/document-to-html.tests.js
+++ b/test/document-to-html.tests.js
@@ -296,6 +296,30 @@ test('subscript runs are wrapped in <sub> tags', function() {
     });
 });
 
+test('all caps runs are ignored by default', function() {
+    var run = runOfText("Hello.", {isAllCaps: true});
+    var converter = new DocumentConverter();
+    return converter.convertToHtml(run).then(function(result) {
+        assert.equal(result.value, "Hello.");
+    });
+});
+
+test('all caps runs can be configured with style mapping', function() {
+    var run = runOfText("Hello.", {isAllCaps: true});
+    var converter = new DocumentConverter({
+        styleMap: [
+            {
+                from: documentMatchers.allCaps,
+                to: htmlPaths.elements([htmlPaths.element("span")])
+            }
+        ]
+    });
+    return converter.convertToHtml(run).then(function(result) {
+        assert.equal(result.value, "<span>Hello.</span>");
+    });
+});
+
+
 test('small caps runs are ignored by default', function() {
     var run = runOfText("Hello.", {isSmallCaps: true});
     var converter = new DocumentConverter();
diff --git a/test/docx/body-reader.tests.js b/test/docx/body-reader.tests.js
index 62ae12f..adb32f8 100644
--- a/test/docx/body-reader.tests.js
+++ b/test/docx/body-reader.tests.js
@@ -531,6 +531,7 @@ var booleanRunProperties = [
     {name: "isUnderline", tagName: "w:u"},
     {name: "isItalic", tagName: "w:i"},
     {name: "isStrikethrough", tagName: "w:strike"},
+    {name: "isAllCaps", tagName: "w:caps"},
     {name: "isSmallCaps", tagName: "w:smallCaps"}
 ];
 
diff --git a/test/style-reader.tests.js b/test/style-reader.tests.js
index 7b37f25..b77ce7e 100644
--- a/test/style-reader.tests.js
+++ b/test/style-reader.tests.js
@@ -15,11 +15,11 @@ test('styleReader.readHtmlPath', {
     'reads empty path': function() {
         assertHtmlPath("", htmlPaths.empty);
     },
-    
+
     'reads single element': function() {
         assertHtmlPath("p", htmlPaths.elements(["p"]));
     },
-    
+
     'reads choice of elements': function() {
         assertHtmlPath(
             "ul|ol",
@@ -28,18 +28,18 @@ test('styleReader.readHtmlPath', {
             ])
         );
     },
-    
+
     'reads nested elements': function() {
         assertHtmlPath("ul > li", htmlPaths.elements(["ul", "li"]));
     },
-    
+
     'reads class on element': function() {
         var expected = htmlPaths.elements([
             htmlPaths.element("p", {"class": "tip"})
         ]);
         assertHtmlPath("p.tip", expected);
     },
-    
+
     'reads class with escaped colon': function() {
         var expected = htmlPaths.elements([
             htmlPaths.element("p", {"class": "a:b"})
@@ -53,21 +53,21 @@ test('styleReader.readHtmlPath', {
         ]);
         assertHtmlPath("p.tip.help", expected);
     },
-    
+
     'reads when element must be fresh': function() {
         var expected = htmlPaths.elements([
             htmlPaths.element("p", {}, {"fresh": true})
         ]);
         assertHtmlPath("p:fresh", expected);
     },
-    
+
     'reads separator for elements': function() {
         var expected = htmlPaths.elements([
             htmlPaths.element("p", {}, {separator: "x"})
         ]);
         assertHtmlPath("p:separator('x')", expected);
     },
-    
+
     'reads separator with escape sequence': function() {
         var expected = htmlPaths.elements([
             htmlPaths.element("p", {}, {separator: "\r\n\t\'\\"})
@@ -88,21 +88,21 @@ test("styleReader.readDocumentMatcher", {
     "reads plain paragraph": function() {
         assertDocumentMatcher("p", documentMatchers.paragraph());
     },
-    
+
     "reads paragraph with style ID": function() {
         assertDocumentMatcher(
             "p.Heading1",
             documentMatchers.paragraph({styleId: "Heading1"})
         );
     },
-    
+
     "reads paragraph with exact style name": function() {
         assertDocumentMatcher(
             "p[style-name='Heading 1']",
             documentMatchers.paragraph({styleName: documentMatchers.equalTo("Heading 1")})
         );
     },
-    
+
     "reads paragraph with style name prefix": function() {
         assertDocumentMatcher(
             "p[style-name^='Heading']",
@@ -116,14 +116,14 @@ test("styleReader.readDocumentMatcher", {
             documentMatchers.paragraph({list: {isOrdered: true, levelIndex: 0}})
         );
     },
-    
+
     "reads p:unordered-list(1) as unordered list with index of 0": function() {
         assertDocumentMatcher(
             "p:unordered-list(1)",
             documentMatchers.paragraph({list: {isOrdered: false, levelIndex: 0}})
         );
     },
-    
+
     "reads plain run": function() {
         assertDocumentMatcher(
             "r",
@@ -152,36 +152,43 @@ test("styleReader.readDocumentMatcher", {
             })
         );
     },
-    
+
     "reads bold": function() {
         assertDocumentMatcher(
             "b",
             documentMatchers.bold
         );
     },
-    
+
     "reads italic": function() {
         assertDocumentMatcher(
             "i",
             documentMatchers.italic
         );
     },
-    
+
     "reads underline": function() {
         assertDocumentMatcher(
             "u",
             documentMatchers.underline
         );
     },
-    
+
     "reads strikethrough": function() {
         assertDocumentMatcher(
             "strike",
             documentMatchers.strikethrough
         );
     },
-    
-    "reads smallcaps": function() {
+
+    "reads all-caps": function() {
+        assertDocumentMatcher(
+            "all-caps",
+            documentMatchers.allCaps
+        );
+    },
+
+    "reads small-caps": function() {
         assertDocumentMatcher(
             "small-caps",
             documentMatchers.smallCaps
@@ -194,21 +201,21 @@ test("styleReader.readDocumentMatcher", {
             documentMatchers.commentReference
         );
     },
-    
+
     "reads line breaks": function() {
         assertDocumentMatcher(
             "br[type='line']",
             documentMatchers.lineBreak
         );
     },
-    
+
     "reads page breaks": function() {
         assertDocumentMatcher(
             "br[type='page']",
             documentMatchers.pageBreak
         );
     },
-    
+
     "reads column breaks": function() {
         assertDocumentMatcher(
             "br[type='column']",
@@ -217,7 +224,7 @@ test("styleReader.readDocumentMatcher", {
     }
 
 });
-    
+
 function assertDocumentMatcher(input, expected) {
     assert.deepEqual(readDocumentMatcher(input), results.success(expected));
 }
@@ -232,7 +239,7 @@ test("styleReader.read", {
             }
         );
     },
-    
+
     "reads style mapping with no HTML path": function() {
         assertStyleMapping(
             "r =>",
@@ -242,7 +249,7 @@ test("styleReader.read", {
             }
         );
     },
-    
+
     "error when not all input is consumed": function() {
         assert.deepEqual(
             readStyle("r => span a"),