@hyperlex/mammoth 1.4.9-beta → 1.4.21

package/lib/docx/numbering-xml.js

@@ -1,13 +1,28 @@
+var _ = require("underscore");
+
 exports.readNumberingXml = readNumberingXml;
 exports.Numbering = Numbering;
-exports.defaultNumbering = new Numbering({});
+exports.defaultNumbering = new Numbering({}, {});
 
 function Numbering(nums, abstractNums, styles) {
+    var allLevels = _.flatten(_.values(abstractNums).map(function(abstractNum) {
+        return _.values(abstractNum.levels);
+    }));
+
+    var levelsByParagraphStyleId = _.indexBy(
+        allLevels.filter(function(level) {
+            return level.paragraphStyleId != null;
+        }),
+        "paragraphStyleId"
+    );
+
     function findLevel(numId, level) {
         var num = nums[numId];
         if (num) {
             var abstractNum = abstractNums[num.abstractNumId];
-            if (abstractNum.numStyleLink == null) {
+            if (!abstractNum) {
+                return null;
+            } else if (abstractNum.numStyleLink == null) {
                 return abstractNums[num.abstractNumId].levels[level];
             } else {
                 var style = styles.findNumberingStyleById(abstractNum.numStyleLink);
@@ -18,8 +33,13 @@ function Numbering(nums, abstractNums, styles) {
         }
     }
 
+    function findLevelByParagraphStyleId(styleId) {
+        return levelsByParagraphStyleId[styleId] || null;
+    }
+
     return {
-        findLevel: findLevel
+        findLevel: findLevel,
+        findLevelByParagraphStyleId: findLevelByParagraphStyleId
     };
 }
 
@@ -47,9 +67,12 @@ function readAbstractNum(element) {
     element.getElementsByTagName("w:lvl").forEach(function(levelElement) {
         var levelIndex = levelElement.attributes["w:ilvl"];
         var numFmt = levelElement.first("w:numFmt").attributes["w:val"];
+        var paragraphStyleId = levelElement.firstOrEmpty("w:pStyle").attributes["w:val"];
+
         levels[levelIndex] = {
             isOrdered: numFmt !== "bullet",
-            level: levelIndex
+            level: levelIndex,
+            paragraphStyleId: paragraphStyleId
         };
     });
 

package/lib/index.d.ts

@@ -0,0 +1,78 @@
+interface Mammoth {
+    convertToHtml: (input: Input, options?: Options) => Promise<Result>;
+    extractRawText: (input: Input) => Promise<Result>;
+    embedStyleMap: (input: Input, styleMap: string) => Promise<{toBuffer: () => Buffer}>;
+    images: Images;
+}
+
+type Input = NodeJsInput | BrowserInput;
+
+type NodeJsInput = PathInput | BufferInput;
+
+interface PathInput {
+    path: string;
+}
+
+interface BufferInput {
+    buffer: Buffer;
+}
+
+type BrowserInput = ArrayBufferInput;
+
+interface ArrayBufferInput {
+    arrayBuffer: ArrayBuffer;
+}
+
+interface Options {
+    styleMap?: string | Array<string>;
+    includeEmbeddedStyleMap?: boolean;
+    includeDefaultStyleMap?: boolean;
+    convertImage?: ImageConverter;
+    ignoreEmptyParagraphs?: boolean;
+    idPrefix?: string;
+}
+
+interface ImageConverter {
+    __mammothBrand: "ImageConverter";
+}
+
+interface Image {
+    contentType: string;
+    read: ImageRead;
+}
+
+interface ImageRead {
+    (): Promise<Buffer>;
+    (encoding: string): Promise<string>;
+}
+
+interface ImageAttributes {
+    src: string;
+}
+
+interface Images {
+    dataUri: ImageConverter;
+    imgElement: (f: (image: Image) => Promise<ImageAttributes>) => ImageConverter;
+}
+
+interface Result {
+    value: string;
+    messages: Array<Message>;
+}
+
+type Message = Warning | Error;
+
+interface Warning {
+    type: "warning";
+    message: string;
+}
+
+interface Error {
+    type: "error";
+    message: string;
+    error: unknown;
+}
+
+declare const mammoth: Mammoth;
+
+export = mammoth;

package/lib/index.js

@@ -3,6 +3,7 @@ var _ = require("underscore");
 var docxReader = require("./docx/docx-reader");
 var docxStyleMap = require("./docx/style-map");
 var DocumentConverter = require("./document-to-html").DocumentConverter;
+var convertElementToRawText = require("./raw-text").convertElementToRawText;
 var readStyle = require("./style-reader").readStyle;
 var readOptions = require("./options-reader").readOptions;
 var unzip = require("./unzip");
@@ -89,23 +90,19 @@ function extractRawText(input) {
         });
 }
 
-function convertElementToRawText(element) {
-    if (element.type === "text") {
-        return element.value;
-    } else {
-        var tail = element.type === "paragraph" ? "\n\n" : "";
-        return (element.children || []).map(convertElementToRawText).join("") + tail;
-    }
-}
-
 function embedStyleMap(input, styleMap) {
     return unzip.openZip(input)
         .tap(function(docxFile) {
             return docxStyleMap.writeStyleMap(docxFile, styleMap);
         })
         .then(function(docxFile) {
+            return docxFile.toBuffer();
+        })
+        .then(function(buffer) {
             return {
-                toBuffer: docxFile.toBuffer
+                toBuffer: function() {
+                    return buffer;
+                }
             };
         });
 }

package/lib/raw-text.js

@@ -0,0 +1,14 @@
+var documents = require("./documents");
+
+function convertElementToRawText(element) {
+    if (element.type === "text") {
+        return element.value;
+    } else if (element.type === documents.types.tab) {
+        return "\t";
+    } else {
+        var tail = element.type === "paragraph" ? "\n\n" : "";
+        return (element.children || []).map(convertElementToRawText).join("") + tail;
+    }
+}
+
+exports.convertElementToRawText = convertElementToRawText;

package/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

package/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"});

package/lib/zipfile.js

@@ -1,41 +1,41 @@
 var JSZip = require("jszip");
 
-var promises = require("./promises");
-
 exports.openArrayBuffer = openArrayBuffer;
 exports.splitPath = splitPath;
 exports.joinPath = joinPath;
 
 function openArrayBuffer(arrayBuffer) {
-    var zipFile = new JSZip(arrayBuffer);
-    function exists(name) {
-        return zipFile.file(name) !== null;
-    }
+    return JSZip.loadAsync(arrayBuffer).then(function(zipFile) {
+        function exists(name) {
+            return zipFile.file(name) !== null;
+        }
 
-    function read(name, encoding) {
-        var array = zipFile.file(name).asUint8Array();
-        var buffer = uint8ArrayToBuffer(array);
-        if (encoding) {
-            return promises.when(buffer.toString(encoding));
-        } else {
-            return promises.when(buffer);
+        function read(name, encoding) {
+            return zipFile.file(name).async("uint8array").then(function(array) {
+                var buffer = uint8ArrayToBuffer(array);
+                if (encoding) {
+                    return buffer.toString(encoding);
+                } else {
+                    return buffer;
+                }
+            });
         }
-    }
 
-    function write(name, contents) {
-        zipFile.file(name, contents);
-    }
+        function write(name, contents) {
+            zipFile.file(name, contents);
+        }
 
-    function toBuffer() {
-        return zipFile.generate({type: "nodebuffer"});
-    }
+        function toBuffer() {
+            return zipFile.generateAsync({type: "nodebuffer"});
+        }
 
-    return {
-        exists: exists,
-        read: read,
-        write: write,
-        toBuffer: toBuffer
-    };
+        return {
+            exists: exists,
+            read: read,
+            write: write,
+            toBuffer: toBuffer
+        };
+    });
 }
 
 function uint8ArrayToBuffer(array) {