2017-06-12 04:04:07 +08:00
|
|
|
function html2notecase(contents, note) {
|
2017-08-24 08:35:47 +08:00
|
|
|
// remove any possible extra newlines which might be inserted - all relevant new lines should be only in <br> and <p>
|
|
|
|
contents = contents.replace(/(?:\r\n|\r|\n)/, '');
|
|
|
|
|
2017-06-12 04:04:07 +08:00
|
|
|
contents = contents.replace(/<br \/>/g, '\n');
|
|
|
|
contents = contents.replace(/<br>/g, '\n');
|
|
|
|
contents = contents.replace(/<\/p>/g, '\n');
|
|
|
|
contents = contents.replace(/<p>/g, '');
|
2017-08-14 09:42:10 +08:00
|
|
|
contents = contents.replace(/ /g, ' ');
|
2017-06-12 04:04:07 +08:00
|
|
|
|
|
|
|
let index = 0;
|
|
|
|
|
|
|
|
note.formatting = [];
|
|
|
|
note.links = [];
|
|
|
|
note.images = [];
|
|
|
|
|
|
|
|
while (index < contents.length) {
|
2017-08-22 09:31:23 +08:00
|
|
|
let curContent = contents.substr(index);
|
2017-08-14 10:35:04 +08:00
|
|
|
|
2017-08-22 09:31:23 +08:00
|
|
|
if (contents[index] === '<') {
|
|
|
|
let found = false;
|
2017-06-12 04:04:07 +08:00
|
|
|
let endOfTag = curContent.indexOf('>');
|
|
|
|
|
2017-08-22 09:31:23 +08:00
|
|
|
if (endOfTag === -1) {
|
2017-06-12 04:04:07 +08:00
|
|
|
console.log("Can't find the end of the tag");
|
|
|
|
}
|
|
|
|
|
|
|
|
let curTag = curContent.substr(0, endOfTag + 1);
|
|
|
|
|
|
|
|
//console.log(contents);
|
|
|
|
|
|
|
|
for (tagId in tags) {
|
|
|
|
let tag = tags[tagId];
|
|
|
|
|
2017-08-22 09:31:23 +08:00
|
|
|
if (contents.substr(index, tag.length) === tag) {
|
2017-06-12 04:04:07 +08:00
|
|
|
found = true;
|
|
|
|
// if (tagMap.get(index) == undefined) {
|
|
|
|
// tagMap.get(index) = [];
|
|
|
|
// }
|
|
|
|
|
|
|
|
// tagMap.get(index).push(key);
|
|
|
|
|
|
|
|
note.formatting.push({
|
|
|
|
note_id: note.detail.note_id,
|
|
|
|
note_offset: index,
|
|
|
|
fmt_tag: tagId,
|
|
|
|
fmt_color: '',
|
|
|
|
fmt_font: '',
|
|
|
|
fmt_value: 100
|
|
|
|
});
|
|
|
|
|
|
|
|
contents = contents.substr(0, index) + contents.substr(index + tag.length);
|
|
|
|
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2017-08-22 09:31:23 +08:00
|
|
|
if (curTag.substr(0, 4) === "<img") {
|
2017-06-12 04:04:07 +08:00
|
|
|
//console.log("Found img tag");
|
|
|
|
|
|
|
|
let dataImagePos = curTag.indexOf('data:image/');
|
|
|
|
|
2017-08-22 09:31:23 +08:00
|
|
|
if (dataImagePos !== -1) {
|
2017-06-12 04:04:07 +08:00
|
|
|
let imageType = curTag.substr(dataImagePos + 11, 3);
|
|
|
|
|
|
|
|
//console.log("image type: " + imageType);
|
|
|
|
|
|
|
|
let dataStart = curTag.substr(dataImagePos + 22);
|
|
|
|
|
|
|
|
let endOfDataPos = dataStart.indexOf('"');
|
|
|
|
|
2017-08-22 09:31:23 +08:00
|
|
|
if (endOfDataPos !== -1) {
|
2017-06-12 04:04:07 +08:00
|
|
|
//console.log("Found the end of image data");
|
|
|
|
|
|
|
|
let imageData = dataStart.substr(0, endOfDataPos);
|
|
|
|
|
|
|
|
note.images.push({
|
|
|
|
note_id: note.detail.note_id,
|
|
|
|
note_offset: index,
|
2017-08-22 09:31:23 +08:00
|
|
|
is_png: imageType === "png",
|
2017-06-12 04:04:07 +08:00
|
|
|
image_data: imageData
|
|
|
|
});
|
|
|
|
|
|
|
|
contents = contents.substr(0, index) + contents.substr(index + curTag.length);
|
|
|
|
|
|
|
|
//console.log("Parsed image: " + imageData.substr(0, 100));
|
|
|
|
|
|
|
|
found = true;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2017-08-14 10:35:04 +08:00
|
|
|
let match = /^<a[^>]+?href="([^"]+?)"[^>]+?>([^<]+?)<\/a>/.exec(curContent);
|
2017-06-12 04:04:07 +08:00
|
|
|
|
2017-08-22 09:31:23 +08:00
|
|
|
if (match !== null) {
|
2017-06-12 04:04:07 +08:00
|
|
|
note.links.push({
|
|
|
|
note_id: note.detail.note_id,
|
|
|
|
note_offset: index,
|
|
|
|
target_url: match[1],
|
|
|
|
lnk_text: match[2]
|
|
|
|
});
|
|
|
|
|
|
|
|
//console.log("Found link with text: " + match[2] + ", targetting: " + match[1]);
|
|
|
|
|
|
|
|
contents = contents.substr(0, index) + match[2] + contents.substr(index + match[0].length);
|
|
|
|
|
|
|
|
found = true;
|
|
|
|
}
|
|
|
|
|
|
|
|
// let imageRegex = /<img[^>]+src="data:image\/(jpg|png);base64,([^>\"]+)"[^>]+>/;
|
|
|
|
|
|
|
|
// console.log("Testing for image: " + curTag.substr(0, 100));
|
|
|
|
// console.log("End of image: " + curTag.substr(curTag.length - 100));
|
|
|
|
|
|
|
|
// let match = imageRegex.exec(curTag);
|
|
|
|
|
|
|
|
// if (match != null) {
|
|
|
|
|
|
|
|
// }
|
|
|
|
|
2017-08-14 10:35:04 +08:00
|
|
|
if (!found) {
|
|
|
|
contents = contents.substr(0, index) + contents.substr(index + endOfTag + 1);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else {
|
2017-08-23 08:19:46 +08:00
|
|
|
let linkMatch = /^(https?|ftp|file):\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|]/i.exec(curContent);
|
2017-08-22 09:31:23 +08:00
|
|
|
|
|
|
|
if (linkMatch !== null) {
|
|
|
|
note.links.push({
|
|
|
|
note_id: note.detail.note_id,
|
|
|
|
note_offset: index,
|
2017-08-23 08:19:46 +08:00
|
|
|
target_url: linkMatch[0],
|
|
|
|
lnk_text: linkMatch[0]
|
2017-08-22 09:31:23 +08:00
|
|
|
});
|
|
|
|
|
2017-08-23 08:19:46 +08:00
|
|
|
console.log(linkMatch[0]);
|
|
|
|
console.log(linkMatch[0].length);
|
|
|
|
|
|
|
|
index += linkMatch[0].length;
|
2017-08-22 09:31:23 +08:00
|
|
|
}
|
|
|
|
else {
|
|
|
|
index++;
|
|
|
|
}
|
2017-06-12 04:04:07 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
note.detail.note_text = contents;
|
|
|
|
}
|