コミット: 911ecc9226ff9d2f40452d0b6588da589efa6f9c - pagewriter (git)

wiki style document editor

コミットメタ情報

• リビジョン: 911ecc9226ff9d2f40452d0b6588da589efa6f9c (tree)
• 日時: 2014-09-01 21:26:22
• 作者: Hiromichi Matsushima <hylom@Hiro...>
• コミッター: Hiromichi Matsushima

ログメッセージ

export: separate text parser for export

変更サマリ

• modified: tools/export/export-single.js
• add: tools/export/export_parser.js

差分

--- a/tools/export/export-single.js
+++ b/tools/export/export-single.js
@@ -4,11 +4,10 @@
  * node export-single.js <target directory> <output directory>
  */
 
-var config = require('../../config');
 var path = require('path');
 var fs = require('fs');
-var child_process = require('child_process');
-var util = require('util');
+
+var exportParser = require('./export_parser');
 
 var HTML_HEADER = 'header.txt';
 var HTML_FOOTER = 'footer.txt';
@@ -65,7 +64,7 @@ function exportSingle(target, output, chapter, pageStart, pageCount) {
       return;
     }
 
-    var result = parseText(data, target);
+    var result = exportParser.parseText(data, target);
 
     // create output directory
     if (!fs.existsSync(output)) {
@@ -98,286 +97,6 @@ function exportSingle(target, output, chapter, pageStart, pageCount) {
   });
 }
 
-function findFigureFile(caption, imageDir) {
-  var figId = caption.match(/^☆図([0-9]+-[0-9]+)/);
-  var figName = 'fig' + figId[1] + '.fw.png';
-  if (isExistsFigure(figName, imageDir)) {
-    return figName;
-  }
-  return '';
-}
-
-function findImageFile(name, targetDir) {
-  if (fs.existsSync(path.join(targetDir, name))) {
-    return name;
-  }
-  var files = fs.readdirSync(targetDir);
-  var exts = config.figureFormat;
-  for (var i = 0; i < files.length; i++) {
-    for (var j = 0; j < exts.length; j++) {
-      if (files[i].indexOf(name + exts[j]) != 0) {
-        return name + exts[j];
-      }
-    }
-  }
-  return '';
-}
-
-// split body-text and others
-function splitBody(lines) {
-  // split honmon and caption
-  var counter = 0;
-  var isCaption = false;
-
-  var bodies = [];
-  var captions = [];
-
-  for (i = 0; i < lines.length; i++) {
-    if (lines[i].match(/^＞＞＞＞/)) {
-      captions.push(lines[i]);
-      i++;
-      while (!lines[i].match(/^＞＞＞＞/)) {
-        captions.push(lines[i]);
-        i++;
-      }
-      continue;
-    }
-
-    if (i >= lines.length) {
-      break;
-    }
-
-    // cleanup blank line
-    if (lines[i].match(/^\s+$/)) {
-      lines[i] = '';
-    }
-
-    // end
-    if ( lines[i] === ''
-         && bodies.length > 0
-         && bodies[bodies.length-1] === '' ) {
-      // do nothing
-    } else {
-      // *図、*表を置換
-      lines[i] = lines[i].replace(/\*図/g, '★図');
-      lines[i] = lines[i].replace(/\*表/g, '★表');
-      bodies.push(lines[i]);
-    }
-  }
-
-  var result = {
-    bodies: bodies,
-    blockItems: captions
-  }
-  return result;
-}
-
-function createFigureList(lines, imageDir) {
-  var figureList = [];
-  var figMode = false;
-  var currentFigure;
-
-  for (var i = 0; i < lines.length; i++) {
-    if (lines[i].match(/^＞＞＞＞/)) {
-      figMode = false;
-      continue;
-    }
-
-    if (lines[i].match(/^＝＝＝＝/)) {
-      figMode = false;
-      continue;
-    }
-
-    if (lines[i].match(/^☆図/)) {
-      figMode = true;
-      currentFigure = findFigureFile(lines[i], imageDir);
-      if (currentFigure != '') {
-        figureList.push(currentFigure);
-      }
-      continue;
-    }
-
-    if (figMode) {
-      if (lines[i].match(/^\s*$/)) {
-        continue;
-      }
-      var fullPath = findImageFile(lines[i], imageDir);
-      figureList.push(fullPath);
-      continue;
-    }
-  }
-  return figureList;
-}
-
-function extractCaptions(lines, imageDir) {
-  var captions = [];
-  var figMode = false;
-  var currentFigure;
-
-  for (var i = 0; i < lines.length; i++) {
-    if (lines[i].match(/^＞＞＞＞/)) {
-      figMode = false;
-      continue;
-    }
-
-    if (lines[i].match(/^＝＝＝＝/)) {
-      figMode = false;
-      captions.push('');
-      continue;
-    }
-
-    if (lines[i].match(/^☆図/)) {
-      captions.push('');
-      captions.push(lines[i]);
-      figMode = true;
-      currentFigure = findFigureFile(lines[i], imageDir);
-      /*
-      if (currentFigure != '') {
-        captions.push(currentFigure);
-      }
-      */
-      continue;
-    }
-
-    if (figMode) {
-      if (currentFigure != '') {
-        continue;
-      }
-      if (lines[i].match(/^\s*$/)) {
-        continue;
-      }
-      var fullPath = findImageFile(lines[i], imageDir);
-      /*
-      captions.push(fullPath);
-      */
-      continue;
-    }
-    captions.push(lines[i]);
-  }
-  return captions;
-}
-
-function isExistsFigure(figName, targetDir) {
-  var fullPath = path.join(targetDir, figName);
-  return fs.existsSync(fullPath);
-}
-
-function makeHtmls(lines, imageDir) {
-  var html = [];
-  var figMode = false;
-  var figTextMode = false;
-  var assumedFigName;
-  var figName
-  var figId;
-  for (var i = 0; i < lines.length; i++) {
-
-    if (lines[i].match(/^＞＞＞＞/)) {
-      figMode = false;
-      continue;
-    }
-
-    // figure
-    if (lines[i].match(/^☆図/)) {
-      figId = lines[i].match(/^☆図([0-9]+-[0-9]+)/);
-      console.log(lines[i]);
-      assumedFigName = 'fig' + figId[1] + '.fw.png';
-      figMode = true;
-      if (isExistsFigure(assumedFigName, imageDir)) {
-        html.push('<span class="caption">' + lines[i] + '</span>');
-        html.push('<img src="figures/' + assumedFigName + '">');
-        html.push('<span class="filename">' + assumedFigName + '</span>');
-        i++;
-        while((i < lines.length) && (!lines[i].match(/^＞＞＞＞/))) {
-          if (lines[i].match(/^\s*$/)) {
-            i++;
-            continue;
-          }
-          if (lines[i].match(/^＝＝＝＝/)) {
-            figMode = false;
-          }
-          if (figMode) {
-            figName = findImageFile(lines[i], imageDir);
-            if ((figName != '') && (figName != assumedFigName)) {
-              html.push('<span class="filename">' + figName + '</span>');
-            }
-          }
-          i++;
-        }
-        continue;
-      }
-      figMode = true;
-      html.push('<span class="caption">' + lines[i] + '</span>');
-      continue;
-    }
-
-    if (lines[i].match(/^＝＝＝＝/)) {
-      i++;
-      while(!lines[i].match(/^＞＞＞＞/)) {
-        i++;
-      }
-      continue;
-    }
-
-    // figure mode
-    if (figMode) {
-      if (lines[i].match(/^\s*$/)) {
-        continue;
-      }
-      figName = findImageFile(lines[i], imageDir);
-      if (figName != '') {
-        html.push('<img src="figures/' + figName + '">');
-        html.push('<span class="filename">' + figName + '</span>');
-      }
-      continue;
-    }
-
-    // table 
-    if (lines[i].match(/^☆表/)) {
-      html.push('<span class="caption">' + lines[i] + '</span>');
-      html.push('<table>');
-      i++;
-      while((i < lines.length) && (!lines[i].match(/^\s*$/))) {
-        if (lines[i].match(/^＞＞＞＞/)) {
-          break;
-        }
-        html.push(lines[i].replace(/^/, '<tr><td>')
-                  .replace(/$/, '</td></tr>')
-                  .replace(/\t/, '</td><td>'));
-        i++;
-      }
-      html.push('</table>');
-      continue;
-    }
-
-    // others
-    html.push(lines[i]);
-  }
-  return html;
-}
-
-// parse main text to separate body text and captions/tables
-function parseText(data, target) {
-  var lines = data.split('\n');
-  var targetDir = path.dirname(target);
-  var imageDir = path.join(targetDir, 'figure');
-
-  // split body and others
-  // result.bodies:
-  // result.blockItems: 
-  var result = splitBody(lines);
-
-  // generate captions
-  result.captions = extractCaptions(result.blockItems, imageDir)
-
-  // generate htmls
-  result.htmls = makeHtmls(result.blockItems, imageDir);
-
-  // generate Figure List
-  result.figures = createFigureList(result.blockItems, imageDir);
-
-  return result;
-}
-
 module.exports = exportSingle;
 
 // main action

--- /dev/null
+++ b/tools/export/export_parser.js
@@ -0,0 +1,289 @@
+
+var path = require('path');
+var fs = require('fs');
+var config = require('../../config');
+
+function findFigureFile(caption, imageDir) {
+  var figId = caption.match(/^☆図([0-9]+-[0-9]+)/);
+  var figName = 'fig' + figId[1] + '.fw.png';
+  if (isExistsFigure(figName, imageDir)) {
+    return figName;
+  }
+  return '';
+}
+
+function findImageFile(name, targetDir) {
+  if (fs.existsSync(path.join(targetDir, name))) {
+    return name;
+  }
+  var files = fs.readdirSync(targetDir);
+  var exts = config.figureFormat;
+  for (var i = 0; i < files.length; i++) {
+    for (var j = 0; j < exts.length; j++) {
+      if (files[i].indexOf(name + exts[j]) != 0) {
+        return name + exts[j];
+      }
+    }
+  }
+  return '';
+}
+
+// split body-text and others
+function splitBody(lines) {
+  // split honmon and caption
+  var counter = 0;
+  var isCaption = false;
+
+  var bodies = [];
+  var captions = [];
+
+  for (i = 0; i < lines.length; i++) {
+    if (lines[i].match(/^＞＞＞＞/)) {
+      captions.push(lines[i]);
+      i++;
+      while (!lines[i].match(/^＞＞＞＞/)) {
+        captions.push(lines[i]);
+        i++;
+      }
+      continue;
+    }
+
+    if (i >= lines.length) {
+      break;
+    }
+
+    // cleanup blank line
+    if (lines[i].match(/^\s+$/)) {
+      lines[i] = '';
+    }
+
+    // end
+    if ( lines[i] === ''
+         && bodies.length > 0
+         && bodies[bodies.length-1] === '' ) {
+      // do nothing
+    } else {
+      // *図、*表を置換
+      lines[i] = lines[i].replace(/\*図/g, '★図');
+      lines[i] = lines[i].replace(/\*表/g, '★表');
+      bodies.push(lines[i]);
+    }
+  }
+
+  var result = {
+    bodies: bodies,
+    blockItems: captions
+  }
+  return result;
+}
+
+function createFigureList(lines, imageDir) {
+  var figureList = [];
+  var figMode = false;
+  var currentFigure;
+
+  for (var i = 0; i < lines.length; i++) {
+    if (lines[i].match(/^＞＞＞＞/)) {
+      figMode = false;
+      continue;
+    }
+
+    if (lines[i].match(/^＝＝＝＝/)) {
+      figMode = false;
+      continue;
+    }
+
+    if (lines[i].match(/^☆図/)) {
+      figMode = true;
+      currentFigure = findFigureFile(lines[i], imageDir);
+      if (currentFigure != '') {
+        figureList.push(currentFigure);
+      }
+      continue;
+    }
+
+    if (figMode) {
+      if (lines[i].match(/^\s*$/)) {
+        continue;
+      }
+      var fullPath = findImageFile(lines[i], imageDir);
+      figureList.push(fullPath);
+      continue;
+    }
+  }
+  return figureList;
+}
+
+function extractCaptions(lines, imageDir) {
+  var captions = [];
+  var figMode = false;
+  var currentFigure;
+
+  for (var i = 0; i < lines.length; i++) {
+    if (lines[i].match(/^＞＞＞＞/)) {
+      figMode = false;
+      continue;
+    }
+
+    if (lines[i].match(/^＝＝＝＝/)) {
+      figMode = false;
+      captions.push('');
+      continue;
+    }
+
+    if (lines[i].match(/^☆図/)) {
+      captions.push('');
+      captions.push(lines[i]);
+      figMode = true;
+      currentFigure = findFigureFile(lines[i], imageDir);
+      /*
+      if (currentFigure != '') {
+        captions.push(currentFigure);
+      }
+      */
+      continue;
+    }
+
+    if (figMode) {
+      if (currentFigure != '') {
+        continue;
+      }
+      if (lines[i].match(/^\s*$/)) {
+        continue;
+      }
+      var fullPath = findImageFile(lines[i], imageDir);
+      /*
+      captions.push(fullPath);
+      */
+      continue;
+    }
+    captions.push(lines[i]);
+  }
+  return captions;
+}
+
+function isExistsFigure(figName, targetDir) {
+  var fullPath = path.join(targetDir, figName);
+  return fs.existsSync(fullPath);
+}
+
+function makeHtmls(lines, imageDir) {
+  var html = [];
+  var figMode = false;
+  var figTextMode = false;
+  var assumedFigName;
+  var figName
+  var figId;
+  for (var i = 0; i < lines.length; i++) {
+
+    if (lines[i].match(/^＞＞＞＞/)) {
+      figMode = false;
+      continue;
+    }
+
+    // figure
+    if (lines[i].match(/^☆図/)) {
+      figId = lines[i].match(/^☆図([0-9]+-[0-9]+)/);
+      console.log(lines[i]);
+      assumedFigName = 'fig' + figId[1] + '.fw.png';
+      figMode = true;
+      if (isExistsFigure(assumedFigName, imageDir)) {
+        html.push('<span class="caption">' + lines[i] + '</span>');
+        html.push('<img src="figures/' + assumedFigName + '">');
+        html.push('<span class="filename">' + assumedFigName + '</span>');
+        i++;
+        while((i < lines.length) && (!lines[i].match(/^＞＞＞＞/))) {
+          if (lines[i].match(/^\s*$/)) {
+            i++;
+            continue;
+          }
+          if (lines[i].match(/^＝＝＝＝/)) {
+            figMode = false;
+          }
+          if (figMode) {
+            figName = findImageFile(lines[i], imageDir);
+            if ((figName != '') && (figName != assumedFigName)) {
+              html.push('<span class="filename">' + figName + '</span>');
+            }
+          }
+          i++;
+        }
+        continue;
+      }
+      figMode = true;
+      html.push('<span class="caption">' + lines[i] + '</span>');
+      continue;
+    }
+
+    if (lines[i].match(/^＝＝＝＝/)) {
+      i++;
+      while(!lines[i].match(/^＞＞＞＞/)) {
+        i++;
+      }
+      continue;
+    }
+
+    // figure mode
+    if (figMode) {
+      if (lines[i].match(/^\s*$/)) {
+        continue;
+      }
+      figName = findImageFile(lines[i], imageDir);
+      if (figName != '') {
+        html.push('<img src="figures/' + figName + '">');
+        html.push('<span class="filename">' + figName + '</span>');
+      }
+      continue;
+    }
+
+    // table 
+    if (lines[i].match(/^☆表/)) {
+      html.push('<span class="caption">' + lines[i] + '</span>');
+      html.push('<table>');
+      i++;
+      while((i < lines.length) && (!lines[i].match(/^\s*$/))) {
+        if (lines[i].match(/^＞＞＞＞/)) {
+          break;
+        }
+        html.push(lines[i].replace(/^/, '<tr><td>')
+                  .replace(/$/, '</td></tr>')
+                  .replace(/\t/, '</td><td>'));
+        i++;
+      }
+      html.push('</table>');
+      continue;
+    }
+
+    // others
+    html.push(lines[i]);
+  }
+  return html;
+}
+
+// parse main text to separate body text and captions/tables
+function parseText(data, target) {
+  var lines = data.split('\n');
+  var targetDir = path.dirname(target);
+  var imageDir = path.join(targetDir, 'figure');
+
+  // split body and others
+  // result.bodies:
+  // result.blockItems: 
+  var result = splitBody(lines);
+
+  // generate captions
+  result.captions = extractCaptions(result.blockItems, imageDir)
+
+  // generate htmls
+  result.htmls = makeHtmls(result.blockItems, imageDir);
+
+  // generate Figure List
+  result.figures = createFigureList(result.blockItems, imageDir);
+
+  return result;
+}
+
+var exportParser = {};
+exportParser.parseText = parseText;
+module.exports = exportParser;
+