From cdf1db35fc8e9329f6ac342c81d4d34b4ee1c72c Mon Sep 17 00:00:00 2001 From: notmasteryet Date: Fri, 10 Feb 2012 12:55:11 -0600 Subject: [PATCH 1/5] Using sans-serif instead of loaded fonts; fix IE9 dataset compatibility shim --- web/compatibility.js | 13 ++++++++----- web/viewer.css | 1 + web/viewer.js | 1 - 3 files changed, 9 insertions(+), 6 deletions(-) diff --git a/web/compatibility.js b/web/compatibility.js index b22153516..9f139b7dd 100644 --- a/web/compatibility.js +++ b/web/compatibility.js @@ -217,12 +217,15 @@ var div = document.createElement('div'); if ('dataset' in div) return; // dataset property exists - Object.defineProperty(HTMLElement.prototype, 'dataset', { - get: function htmlElementDatasetGetter() { - // adding dataset field to the actual object - return (this.dataset = {}); + var oldCreateElement = document.createElement; + document.createElement = function newCreateElement() { + var result = oldCreateElement.apply(document, arguments); + if (arguments[0] === 'div') { + // creating dataset property for the div elements + result.dataset = {}; } - }); + return result; + }; })(); // Check console compatability diff --git a/web/viewer.css b/web/viewer.css index 681e5046a..4d0c64dad 100644 --- a/web/viewer.css +++ b/web/viewer.css @@ -252,6 +252,7 @@ canvas { right: 0; bottom: 0; color: #000; + font-family: sans-serif; } .textLayer > div { diff --git a/web/viewer.js b/web/viewer.js index 5a1a1df03..d5162a194 100644 --- a/web/viewer.js +++ b/web/viewer.js @@ -1083,7 +1083,6 @@ var TextLayerBuilder = function textLayerBuilder(textLayerDiv) { textDiv.dataset.canvasWidth = text.canvasWidth * text.geom.hScale; textDiv.style.fontSize = fontHeight + 'px'; - textDiv.style.fontFamily = fontName || 'sans-serif'; textDiv.style.left = text.geom.x + 'px'; textDiv.style.top = (text.geom.y - fontHeight) + 'px'; textDiv.textContent = text.str; From ffa0e082a4338d3cb92bf70935dfae7d68e586e1 Mon Sep 17 00:00:00 2001 From: Adil Allawi Date: Sun, 12 Feb 2012 22:31:30 +0000 Subject: [PATCH 2/5] Scale text divs instead of letterspacing --- web/viewer.js | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/web/viewer.js b/web/viewer.js index d5162a194..9cf97a751 100644 --- a/web/viewer.js +++ b/web/viewer.js @@ -1041,12 +1041,11 @@ var TextLayerBuilder = function textLayerBuilder(textLayerDiv) { textLayerDiv.appendChild(textDiv); if (textDiv.dataset.textLength > 1) { // avoid div by zero - // Adjust div width (via letterSpacing) to match canvas text + // Adjust div width to match canvas text // Due to the .offsetWidth calls, this is slow // This needs to come after appending to the DOM - textDiv.style.letterSpacing = - ((textDiv.dataset.canvasWidth - textDiv.offsetWidth) / - (textDiv.dataset.textLength - 1)) + 'px'; + textDiv.style.MozTransform = 'scale(' + textDiv.dataset.canvasWidth/textDiv.offsetWidth + ',1)'; + textDiv.style.MozTransformOrigin = '0% 0%'; } } // textLength > 0 } From 2bc708305d361b56e6e9b079c73ef199cff6c917 Mon Sep 17 00:00:00 2001 From: Adil Allawi Date: Mon, 13 Feb 2012 02:10:41 +0000 Subject: [PATCH 3/5] Fix up bidi algorithm, and set direction of div to match text direction --- src/bidi.js | 502 +++++++++++++++++++++++++++++--------------------- src/canvas.js | 7 +- web/viewer.js | 3 +- 3 files changed, 294 insertions(+), 218 deletions(-) diff --git a/src/bidi.js b/src/bidi.js index cbb668764..63ca2dde2 100644 --- a/src/bidi.js +++ b/src/bidi.js @@ -1,237 +1,327 @@ -function bidi(doc, str, startLevel) { - if (str.length == 0) return str; - - var chars= new Array(str.length); - var levels = new Array(str.length); - var types = new Array(str.length); - var oldtypes = new Array(str.length); - -// get types, fill arrays - - for (var i = 0; i < str.length; ++i) { +var baseTypes = [ + "BN", "BN", "BN", "BN", "BN", "BN", "BN", "BN", "BN", "S", "B", "S", "WS", + "B", "BN", "BN", /*U+000*/ + "BN", "BN", "BN", "BN", "BN", "BN", "BN", "BN", "BN", "BN", "BN", "BN", "B", + "B", "B", "S", /*U+001*/ + "WS", "ON", "ON", "ET", "ET", "ET", "ON", "ON", "ON", "ON", "ON", "ON", "CS", + "ON", "CS", "ON", /*U+002*/ + "EN", "EN", "EN", "EN", "EN", "EN", "EN", "EN", "EN", "EN", "ON", "ON", "ON", + "ON", "ON", "ON", /*U+003*/ + "ON", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", + "L", /*U+004*/ + "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "ON", "ON", "ON", "ON", + "ON", /*U+005*/ + "ON", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", + "L", /*U+006*/ + "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "ON", "ON", "ON", "ON", + "BN", /*U+007*/ + "BN", "BN", "BN", "BN", "BN", "B", "BN", "BN", "BN", "BN", "BN", "BN", "BN", + "BN", "BN", "BN", /*U+008*/ + "BN", "BN", "BN", "BN", "BN", "BN", "BN", "BN", "BN", "BN", "BN", "BN", "BN", + "BN", "BN", "BN", /*U+009*/ + "CS", "ON", "ET", "ET", "ET", "ET", "ON", "ON", "ON", "ON", "L", "ON", "ON", + "ON", "ON", "ON", /*U+00a*/ + "ET", "ET", "EN", "EN", "ON", "L", "ON", "ON", "ON", "EN", "L", "ON", "ON", + "ON", "ON", "ON", /*U+00b*/ + "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", + "L", /*U+00c*/ + "L", "L", "L", "L", "L", "L", "L", "ON", "L", "L", "L", "L", "L", "L", "L", + "L", /*U+00d*/ + "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", "L", + "L", /*U+00e*/ + "L", "L", "L", "L", "L", "L", "L", "ON", "L", "L", "L", "L", "L", "L", "L", + "L" /*U+00f*/ +]; + +var arabicTypes = [ + "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "CS", + "AL", "ON", "ON", //60 + "NSM", "NSM", "NSM", "NSM", "NSM", "NSM", "AL", "AL", "AL", "AL", "AL", "AL", + "AL", "AL", "AL", "AL", //61 + "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", + "AL", "AL", "AL", //62 + "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", + "AL", "AL", "AL", //63 + "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "NSM", + "NSM", "NSM", "NSM", "NSM", //64 + "NSM", "NSM", "NSM", "NSM", "NSM", "NSM", "NSM", "NSM", "NSM", "AL", "AL", + "AL", "AL", "AL", "AL", "AL", //65 + "AN", "AN", "AN", "AN", "AN", "AN", "AN", "AN", "AN", "AN", "ET", "AN", "AN", + "AL", "AL", "AL", //66 + "NSM", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", + "AL", "AL", "AL", //67 + "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", + "AL", "AL", "AL", //68 + "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", + "AL", "AL", "AL", //69 + "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", + "AL", "AL", "AL", //6a + "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", + "AL", "AL", "AL", //6b + "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", + "AL", "AL", "AL", //6c + "AL", "AL", "AL", "AL", "AL", "AL", "NSM", "NSM", "NSM", "NSM", "NSM", "NSM", + "NSM", "NSM", "NSM", "NSM", //6d + "NSM", "NSM", "NSM", "NSM", "NSM", "NSM", "NSM", "NSM", "NSM", "ON", "NSM", + "NSM", "NSM", "NSM", "AL", "AL", //6e + "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", "AL", + "AL", "AL", "AL" //6f +]; + +function bidi(text, startLevel) { + var str = text.str; + var strLength = str.length; + if (strLength == 0) return str; + + // get types, fill arrays + + var chars = new Array(strLength); + var types = new Array(strLength); + var oldtypes = new Array(strLength); + var numBidi = 0; + + for (var i = 0; i < strLength; ++i) { var c = str.charAt(i); chars[i] = c; - levels[i] = startLevel; var t = "L"; - if ('\u0600' <= c && c <= '\u06ff') t = "AL"; - else if ('0' <= c && c <= '9') t = (c <= 5) ? "EN" : "AN"; - else if (c == '.' || c == ',' || c == ':') t = "CS"; - else if (c == '/') t = "ES"; - else if (c == '#' || c == '$' || c == '%' || c == '+' || c == '-') t = "ET" - else if (c == '>') t = "L" - else if (c == '<') t = "R" + if (c <= '\u00ff') + t = baseTypes[c.charCodeAt(0)]; + else if ('\u0590' <= c && c <= '\u05f4') + t = "R"; + else if ('\u0600' <= c && c <= '\u06ff') + t = arabicTypes[c.charCodeAt(0) & 0xff]; + else if ('\u0700' <= c && c <= '\u08AC') + t = "AL"; + + if (t == "R" || t == "AL" || t == "AN") + numBidi++; oldtypes[i] = types[i] = t; } - var diffChars = new Array(str.length); - var diffLevels = new Array(str.length); - var diffTypes = new Array(str.length); + // detect the bidi method + // if there are no rtl characters then no bidi needed + // if less than 30% chars are rtl then string is primarily ltr + // if more than 30% chars are rtl then string is primarily rtl + if (numBidi == 0) { + text.direction = 'ltr'; + return str; + } + else if (startLevel == -1) { + if ((strLength / numBidi) < 0.3) { + text.direction = 'ltr'; + startLevel = 0; + } else { + text.direction = 'rtl'; + startLevel = 1; + } + } + + var levels = new Array(strLength); + + for (var i = 0; i < strLength; ++i) { + levels[i] = startLevel; + } - showArray(doc, "Chars: ", chars, diffChars); - showArray(doc, "Types: ", types, diffTypes); - //alert("chars: " + chars.join(",")); - //alert("types: " + types.join(",")); - //alert("levels: " + levels.join(",")); + var diffChars = new Array(strLength); + var diffLevels = new Array(strLength); + var diffTypes = new Array(strLength); -/* -X1-X10: skip most of this, since we are NOT doing the embeddings. -*/ + /* + X1-X10: skip most of this, since we are NOT doing the embeddings. + */ var e = isOdd(startLevel) ? "R" : "L"; var sor = e; var eor = sor; -/* -W1. Examine each non-spacing mark (NSM) in the level run, and change the type of the NSM to the type of the previous character. If the NSM is at the start of the level run, it will get the type of sor. -*/ + /* + W1. Examine each non-spacing mark (NSM) in the level run, and change the type + of the NSM to the type of the previous character. If the NSM is at the start + of the level run, it will get the type of sor. + */ var lastType = sor; - for (var i = 0; i < types.length; ++i) { + for (var i = 0; i < strLength; ++i) { if (types[i] == "NSM") types[i] = lastType; else lastType = types[i]; } - showArray(doc, "W1: ", types, diffTypes); - -/* -W2. Search backwards from each instance of a European number until the first strong type (R, L, AL, or sor) is found. If an AL is found, change the type of the European number to Arabic number. -*/ + /* + W2. Search backwards from each instance of a European number until the first + strong type (R, L, AL, or sor) is found. If an AL is found, change the type + of the European number to Arabic number. + */ var lastType = sor; - for (var i = 0; i < types.length; ++i) { + for (var i = 0; i < strLength; ++i) { var t = types[i]; - if (t == "EN") types[i] = (lastType == "AL") ? "AN" : "EN"; - else if (t == "R" || t == "L" || t == "AL") lastType = t; + if (t == "EN") + types[i] = (lastType == "AL") ? "AN" : "EN"; + else if (t == "R" || t == "L" || t == "AL") + lastType = t; } - showArray(doc, "W2: ", types, diffTypes); + /* + W3. Change all ALs to R. + */ -/* -W3. Change all ALs to R. -*/ - - for (var i = 0; i < types.length; ++i) { + for (var i = 0; i < strLength; ++i) { var t = types[i]; if (t == "AL") types[i] = "R"; } - showArray(doc, "W3: ", types, diffTypes); - -/* -W4. A single European separator between two European numbers changes to a European number. A single common separator between two numbers of the same type changes to that type: -*/ - - for (var i = 1; i < types.length - 1; ++i) { - if (types[i] == "ES" && types[i-1] == "EN" && types[i+1] == "EN") types[i] = "EN"; - if (types[i] == "CS" && (types[i-1] == "EN" || types[i-1] == "AN") - && types[i+1] == types[i-1]) types[i] = types[i-1]; + /* + W4. A single European separator between two European numbers changes to a + European number. A single common separator between two numbers of the same + type changes to that type: + */ + + for (var i = 1; i < strLength - 1; ++i) { + if (types[i] == "ES" && types[i - 1] == "EN" && types[i + 1] == "EN") + types[i] = "EN"; + if (types[i] == "CS" && (types[i - 1] == "EN" || types[i - 1] == "AN") && + types[i + 1] == types[i - 1]) + types[i] = types[i - 1]; } - showArray(doc, "W4: ", types, diffTypes); + /* + W5. A sequence of European terminators adjacent to European numbers changes + to all European numbers: + */ -/* -W5. A sequence of European terminators adjacent to European numbers changes to all European numbers: -*/ - - for (var i = 0; i < types.length; ++i) { + for (var i = 0; i < strLength; ++i) { if (types[i] == "EN") { // do before - for (j = i-1; j >= 0; --j) { - if (types[j] == "ET") types[j] = "EN"; + for (j = i - 1; j >= 0; --j) { + if (types[j] == "ET") + types[j] = "EN"; else break; } // do after - for (j = i+1; j < types.length; --j) { - if (types[j] == "ET") types[j] = "EN"; + for (j = i + 1; j < strLength; --j) { + if (types[j] == "ET") + types[j] = "EN"; else break; } } } - showArray(doc, "W5: ", types, diffTypes); - - -/* -W6. Otherwise, separators and terminators change to Other Neutral: -*/ + /* + W6. Otherwise, separators and terminators change to Other Neutral: + */ - for (var i = 0; i < types.length; ++i) { + for (var i = 0; i < strLength; ++i) { var t = types[i]; - if (t == "ES" || t == "ET" || t == "CS") types[i] = "ON"; + if (t == "WS" || t == "ES" || t == "ET" || t == "CS") + types[i] = "ON"; } - showArray(doc, "W6: ", types, diffTypes); - -/* -W7. Search backwards from each instance of a European number until the first strong type (R, L, or sor) is found. If an L is found, then change the type of the European number to L. -*/ + /* + W7. Search backwards from each instance of a European number until the first + strong type (R, L, or sor) is found. If an L is found, then change the type + of the European number to L. + */ var lastType = sor; - for (var i = 0; i < types.length; ++i) { + for (var i = 0; i < strLength; ++i) { var t = types[i]; - if (t == "EN") types[i] = (lastType == "L") ? "L" : "EN"; - else if (t == "R" || t == "L") lastType = t; + if (t == "EN") + types[i] = (lastType == "L") ? "L" : "EN"; + else if (t == "R" || t == "L") + lastType = t; } - showArray(doc, "W7: ", types, diffTypes); - -/* -N1. A sequence of neutrals takes the direction of the surrounding strong text if the text on both sides has the same direction. European and Arabic numbers are treated as though they were R. Start-of-level-run (sor) and end-of-level-run (eor) are used at level run boundaries. -*/ + /* + N1. A sequence of neutrals takes the direction of the surrounding strong text + if the text on both sides has the same direction. European and Arabic numbers + are treated as though they were R. Start-of-level-run (sor) and + end-of-level-run (eor) are used at level run boundaries. + */ - for (var i = 0; i < types.length; ++i) { + for (var i = 0; i < strLength; ++i) { if (types[i] == "ON") { - var end = findUnequal(types, i+1, "ON"); + var end = findUnequal(types, i + 1, "ON"); var before = sor; - if (i > 0) before = types[i-1]; + if (i > 0) + before = types[i - 1]; var after = eor; - if (end+1 < types.length) after = types[end+1]; - if (before != "L") before = "R"; - if (after != "L") after = "R"; - if (before == after) setValues(types, i, end, before); + if (end + 1 < strLength) + after = types[end + 1]; + if (before != "L") + before = "R"; + if (after != "L") + after = "R"; + if (before == after) + setValues(types, i, end, before); i = end - 1; // reset to end (-1 so next iteration is ok) } } - showArray(doc, "N1: ", types, diffTypes); - -/* -N2. Any remaining neutrals take the embedding direction. -*/ + /* + N2. Any remaining neutrals take the embedding direction. + */ - for (var i = 0; i < types.length; ++i) { - if (types[i] == "ON") types[i] = e; + for (var i = 0; i < strLength; ++i) { + if (types[i] == "ON") + types[i] = e; } - showArray(doc, "N2: ", types, diffTypes); + /* + I1. For all characters with an even (left-to-right) embedding direction, + those of type R go up one level and those of type AN or EN go up two levels. + I2. For all characters with an odd (right-to-left) embedding direction, those + of type L, EN or AN go up one level. + */ -/* -I1. For all characters with an even (left-to-right) embedding direction, those of type R go up one level and those of type AN or EN go up two levels. -I2. For all characters with an odd (right-to-left) embedding direction, those of type L, EN or AN go up one level. -*/ - - showArray(doc, "Levels: ", levels, diffLevels); - - for (var i = 0; i < types.length; ++i) { + for (var i = 0; i < strLength; ++i) { var t = types[i]; if (isEven(levels[i])) { if (t == "R") { levels[i] += 1; - } else if (t == "AN" || t == "EN") { + } + else if (t == "AN" || t == "EN") { levels[i] += 2; } - } else { // isOdd, so + } + else { // isOdd, so if (t == "L" || t == "AN" || t == "EN") { levels[i] += 1; } } } - showArray(doc, "I1/2: ", levels, diffLevels); - - -/* -L1. On each line, reset the embedding level of the following characters to the paragraph embedding level: - -segment separators, -paragraph separators, -any sequence of whitespace characters preceding a segment separator or paragraph separator, and -any sequence of white space characters at the end of the line. -*/ - -/* - boolean atEnd = true; - for (var i = levels.length - 1; i >= 0; --i) { - var t = oldTypes[i]; - if (t == "B" || t == "S") { - levels[i] = startLevel; - atEnd = true; - } else if (atEnd && t == "WS") { - levels[i] = startLevel; - } - } -*/ + /* + L1. On each line, reset the embedding level of the following characters to + the paragraph embedding level: - showArray(doc, "L1: ", levels, diffLevels); + segment separators, + paragraph separators, + any sequence of whitespace characters preceding a segment separator or + paragraph separator, and any sequence of white space characters at the end + of the line. + */ + //dont bother as text is only single line -/* -L2. From the highest level found in the text to the lowest odd level on each line, reverse any contiguous sequence of characters that are at that level or higher. -*/ + /* + L2. From the highest level found in the text to the lowest odd level on each + line, reverse any contiguous sequence of characters that are at that level or + higher. + */ // find highest level & lowest odd level var highestLevel = -1; var lowestOddLevel = 99; - // alert("Levels: " + levels.join(",")); for (var i = 0; i < levels.length; ++i) { var level = levels[i]; - if (highestLevel < level) highestLevel = level; - if (lowestOddLevel > level && isOdd(level)) lowestOddLevel = level; + if (highestLevel < level) + highestLevel = level; + if (lowestOddLevel > level && isOdd(level)) + lowestOddLevel = level; } - // alert("highestLevel: " + highestLevel + "; lowestOddLevel: " + lowestOddLevel); // now reverse between those limits @@ -244,49 +334,44 @@ L2. From the highest level found in the text to the lowest odd level on each lin reverseValues(chars, start, i); start = -1; } - } else if (start < 0) { + } + else if (start < 0) { start = i; } } if (start >= 0) { reverseValues(chars, start, levels.length); } - - showArray(doc, "L2 (" + level + "):", chars, diffChars); - } + /* + L3. Combining marks applied to a right-to-left base character will at this + point precede their base character. If the rendering engine expects them to + follow the base characters in the final display process, then the ordering of + the marks and the base character must be reversed. + */ -/* -L3. Combining marks applied to a right-to-left base character will at this point precede their base character. If the rendering engine expects them to follow the base characters in the final display process, then the ordering of the marks and the base character must be reversed. -*/ - -// don't bother for now + // don't bother for now - showArray(doc, "L3: ", chars, diffChars); + /* + L4. A character that possesses the mirrored property as specified by + Section 4.7, Mirrored, must be depicted by a mirrored glyph if the resolved + directionality of that character is R. + */ + //dont mirror as this is already in the pdf -/* -L4. A character that possesses the mirrored property as specified by Section 4.7, Mirrored, must be depicted by a mirrored glyph if the resolved directionality of that character is R. -*/ - - for (var i = 0; i < chars.length; ++i) { - chars[i] = mirrorGlyphs(chars[i]); - } - - showArray(doc, "L4: ", chars, diffChars); - -// Finally, return string + // Finally, return string var result = ""; for (var i = 0; i < chars.length; ++i) { var ch = chars[i]; - if (ch != '<' && ch != '>') result += ch; + if (ch != '<' && ch != '>') + result += ch; } return result; } - // UTILITIES function isOdd(i) { @@ -312,57 +397,50 @@ function setValues(arr, start, end, value) { } function reverseValues(arr, start, end) { - // alert("reverse: " + arr.join(",") + "; " + start + "; " + end); - for (var i = start, j = end-1; i < j; ++i, --j) { + for (var i = start, j = end - 1; i < j; ++i, --j) { var temp = arr[i]; arr[i] = arr[j]; arr[j] = temp; } - // alert("reverse: " + chars.join(",")); } function mirrorGlyphs(c) { -/* -# BidiMirroring-1.txt -0028; 0029 # LEFT PARENTHESIS -0029; 0028 # RIGHT PARENTHESIS -003C; 003E # LESS-THAN SIGN -003E; 003C # GREATER-THAN SIGN -005B; 005D # LEFT SQUARE BRACKET -005D; 005B # RIGHT SQUARE BRACKET -007B; 007D # LEFT CURLY BRACKET -007D; 007B # RIGHT CURLY BRACKET -00AB; 00BB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK -00BB; 00AB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -*/ + /* + # BidiMirroring-1.txt + 0028; 0029 # LEFT PARENTHESIS + 0029; 0028 # RIGHT PARENTHESIS + 003C; 003E # LESS-THAN SIGN + 003E; 003C # GREATER-THAN SIGN + 005B; 005D # LEFT SQUARE BRACKET + 005D; 005B # RIGHT SQUARE BRACKET + 007B; 007D # LEFT CURLY BRACKET + 007D; 007B # RIGHT CURLY BRACKET + 00AB; 00BB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 00BB; 00AB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + */ switch (c) { - case '(': return ')'; - case ')': return '('; - case '<': return '>'; - case '>': return '<'; - case ']': return '['; - case '[': return ']'; - case '}': return '{'; - case '{': return '}'; - case '�': return '�'; - case '�': return '�'; - default: return c; + case '(': + return ')'; + case ')': + return '('; + case '<': + return '>'; + case '>': + return '<'; + case ']': + return '['; + case '[': + return ']'; + case '}': + return '{'; + case '{': + return '}'; + case '�': + return '�'; + case '�': + return '�'; + default: + return c; } } -function showArray(doc, title, arr, diffarr) { - if (doc == null) - return; - var haveDiff = false; - for (var i = 0; i < arr.length; ++i) { - if (arr[i] != diffarr[i]) { - haveDiff = true; - diffarr[i] = arr[i]; - } - } - if (haveDiff) { - doc.writeln("", title, "", arr.join(""), ""); - } -} - - diff --git a/src/canvas.js b/src/canvas.js index 1106ba328..499a26446 100644 --- a/src/canvas.js +++ b/src/canvas.js @@ -824,18 +824,15 @@ var CanvasGraphics = (function CanvasGraphicsClosure() { text.str += shownText.str; } text.canvasWidth += shownText.canvasWidth; - text.length += e.length; + text.length += shownText.length; } } else { malformed('TJ array element ' + e + ' is not string or num'); } } - if (textSelection) { - if (isRTLRangeFor(text.str.charCodeAt(0))) //first char is rtl - text.str = bidi(null, text.str, 1); + if (textSelection) this.textLayer.appendText(text, font.loadedName, fontSize); - } }, nextLineShowText: function canvasGraphicsNextLineShowText(text) { this.nextLine(); diff --git a/web/viewer.js b/web/viewer.js index 9cf97a751..bbb192a9a 100644 --- a/web/viewer.js +++ b/web/viewer.js @@ -1084,7 +1084,8 @@ var TextLayerBuilder = function textLayerBuilder(textLayerDiv) { textDiv.style.fontSize = fontHeight + 'px'; textDiv.style.left = text.geom.x + 'px'; textDiv.style.top = (text.geom.y - fontHeight) + 'px'; - textDiv.textContent = text.str; + textDiv.textContent = bidi(text, -1); + textDiv.dir = text.direction; textDiv.dataset.textLength = text.length; this.textDivs.push(textDiv); }; From 6902ba51fac5237d1a9bff5ad33ca3b23f093087 Mon Sep 17 00:00:00 2001 From: Adil Allawi Date: Mon, 13 Feb 2012 14:27:59 +0000 Subject: [PATCH 4/5] Properly support custom CSS properties Fix comment in bidi --- src/bidi.js | 2 +- src/util.js | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++ web/viewer.js | 6 ++++-- 3 files changed, 56 insertions(+), 3 deletions(-) diff --git a/src/bidi.js b/src/bidi.js index 63ca2dde2..09f8dd7c6 100644 --- a/src/bidi.js +++ b/src/bidi.js @@ -359,7 +359,7 @@ function bidi(text, startLevel) { directionality of that character is R. */ - //dont mirror as this is already in the pdf + //dont mirror as characters are already mirrored in the pdf // Finally, return string diff --git a/src/util.js b/src/util.js index f00fcd1ce..3af6125e3 100644 --- a/src/util.js +++ b/src/util.js @@ -118,6 +118,57 @@ var Util = (function UtilClosure() { return Util; })(); +// optimised CSS custom property getter/setter +var CustomStyle = (function CustomStyleClosure() { + + // As noted on: http://www.zachstronaut.com/posts/2009/02/17/ + // animate-css-transforms-firefox-webkit.html + // in some versions of IE9 it is critical that ms appear in this list + // before Moz + var prefixes = ['ms', 'Moz', 'Webkit', 'O']; + var _cache = { }; + + function CustomStyle() { + } + + CustomStyle.getProp = function get(propName, element) { + // check cache only when no element is given + if (arguments.length == 1 && typeof _cache[propName] == 'string') { + return _cache[propName]; + } + + element = element || document.documentElement; + var style = element.style, prefixed, uPropName; + + // test standard property first + if (typeof style[propName] == 'string') { + return (_cache[propName] = propName); + } + + // capitalize + uPropName = propName.charAt(0).toUpperCase() + propName.slice(1); + + // test vendor specific properties + for (var i = 0, l = prefixes.length; i < l; i++) { + prefixed = prefixes[i] + uPropName; + if (typeof style[prefixed] == 'string') { + return (_cache[propName] = prefixed); + } + } + + //if all fails then set to undefined + return (_cache[propName] = 'undefined'); + } + + CustomStyle.setProp = function set(propName, element, str) { + var prop = this.getProp(propName); + if (prop != 'undefined') + element.style[prop] = str; + } + + return CustomStyle; +})(); + var PDFStringTranslateTable = [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x2D8, 0x2C7, 0x2C6, 0x2D9, 0x2DD, 0x2DB, 0x2DA, 0x2DC, 0, 0, 0, 0, 0, 0, 0, diff --git a/web/viewer.js b/web/viewer.js index bbb192a9a..ff857a943 100644 --- a/web/viewer.js +++ b/web/viewer.js @@ -1044,8 +1044,10 @@ var TextLayerBuilder = function textLayerBuilder(textLayerDiv) { // Adjust div width to match canvas text // Due to the .offsetWidth calls, this is slow // This needs to come after appending to the DOM - textDiv.style.MozTransform = 'scale(' + textDiv.dataset.canvasWidth/textDiv.offsetWidth + ',1)'; - textDiv.style.MozTransformOrigin = '0% 0%'; + CustomStyle.setProp('transform' , textDiv, 'scale(' + + textDiv.dataset.canvasWidth/textDiv.offsetWidth + + ',1)'); + CustomStyle.setProp('transformOrigin' , textDiv, '0% 0%'); } } // textLength > 0 } From b50cf76ab589fa1bb4a52014470274f887e067cd Mon Sep 17 00:00:00 2001 From: Adil Allawi Date: Mon, 13 Feb 2012 14:38:44 +0000 Subject: [PATCH 5/5] Properly integrate new file bidi.js --- Makefile | 1 + src/worker_loader.js | 3 ++- test/test_slave.html | 1 + test/unit/jsTestDriver.conf | 1 + web/viewer.html | 2 +- 5 files changed, 6 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index 043cb7fb5..f515bf717 100644 --- a/Makefile +++ b/Makefile @@ -38,6 +38,7 @@ PDF_JS_FILES = \ worker.js \ ../external/jpgjs/jpg.js \ jpx.js \ + bidi.js \ $(NULL) # make server diff --git a/src/worker_loader.js b/src/worker_loader.js index fc3d7a5f7..69eb1414f 100644 --- a/src/worker_loader.js +++ b/src/worker_loader.js @@ -24,7 +24,8 @@ var files = [ 'stream.js', 'worker.js', '../external/jpgjs/jpg.js', - 'jpx.js' + 'jpx.js', + 'bidi.js' ]; // Load all the files. diff --git a/test/test_slave.html b/test/test_slave.html index a2682a5a6..50bb067e1 100644 --- a/test/test_slave.html +++ b/test/test_slave.html @@ -23,6 +23,7 @@ + - +