extern/pdf-to-markdown
1
0
Fork 0
mirror of https://github.com/jzillmann/pdf-to-markdown.git synced 2024-11-21 23:33:31 +01:00
Code Issues Packages Projects Releases Wiki Activity

rename element type to block type

Browse Source
This commit is contained in:
Johannes Zillmann 2017-03-28 09:11:00 +02:00
parent c4679238cd
commit a0c5bb29d6
8 changed files with 33 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
src/javascript/models/ElementType.jsx → src/javascript/models/markdown/BlockType.jsx
View File

@ -1,14 +1,14 @@
import { Enum } from 'enumify';
import { linesToText } from './markdown/WordType.jsx';
import LineItemBlock from './LineItemBlock.jsx';
import { linesToText } from './WordType.jsx';
import LineItemBlock from '../LineItemBlock.jsx';
// An Markdown element
export default class ElementType extends Enum {
// An Markdown block
export default class BlockType extends Enum {
}
//TODO rename to BlockType
ElementType.initEnum({
BlockType.initEnum({
H1: {
headline: true,
headlineLevel: 1,
@ -84,8 +84,8 @@ ElementType.initEnum({
}
});
export function isHeadline(elementType: ElementType) {
return elementType && elementType.name.length == 2 && elementType.name[0] === 'H'
export function isHeadline(type: BlockType) {
return type && type.name.length == 2 && type.name[0] === 'H'
}
export function blockToText(block: LineItemBlock) {
@ -97,17 +97,17 @@ export function blockToText(block: LineItemBlock) {
export function headlineByLevel(level) {
if (level == 1) {
return ElementType.H1;
return BlockType.H1;
} else if (level == 2) {
return ElementType.H2;
return BlockType.H2;
} else if (level == 3) {
return ElementType.H3;
return BlockType.H3;
} else if (level == 4) {
return ElementType.H4;
return BlockType.H4;
} else if (level == 5) {
return ElementType.H5;
return BlockType.H5;
} else if (level == 6) {
return ElementType.H6;
return BlockType.H6;
}
throw "Unsupported headline level: " + level + " (supported are 1-6)";
}

2
src/javascript/models/transformations/ToTextBlocks.jsx
View File

@ -2,7 +2,7 @@ import React from 'react';
import Transformation from './Transformation.jsx';
import TextPageView from '../../components/debug/TextPageView.jsx';
import ParseResult from '../ParseResult.jsx';
import { blockToText } from '../ElementType.jsx';
import { blockToText } from '../markdown/BlockType.jsx';
export default class ToTextBlocks extends Transformation {

4
src/javascript/models/transformations/textitem/CompactLines.jsx
View File

@ -5,7 +5,7 @@ import ParseResult from '../../ParseResult.jsx';
import LineItem from '../../LineItem.jsx';
import TextItemLineGrouper from '../../TextItemLineGrouper.jsx';
import LineConverter from '../../LineConverter.jsx';
import ElementType from '../../ElementType.jsx';
import BlockType from '../../markdown/BlockType.jsx';
import { REMOVED_ANNOTATION, ADDED_ANNOTATION } from '../../Annotation.jsx';
@ -59,7 +59,7 @@ export default class CompactLines extends ToLineItemTransformation {
foundFootnoteLinks.push.apply(foundFootnoteLinks, footnoteLinks);
}
if (lineItem.parsedElements.footnotes.length > 0) {
lineItem.type = ElementType.FOOTNOTES;
lineItem.type = BlockType.FOOTNOTES;
const footnotes = lineItem.parsedElements.footnotes.map(footnote => <span key={ footnote }><a href={ "#Page " + (page.index + 1) }>{ footnote }</a>,</span>);
foundFootnotes.push.apply(foundFootnotes, footnotes);
}

10
src/javascript/models/transformations/textitem/DetectHeaders.jsx
View File

@ -1,8 +1,8 @@
import ToLineItemTransformation from '../ToLineItemTransformation.jsx';
import ParseResult from '../../ParseResult.jsx';
import { DETECTED_ANNOTATION } from '../../Annotation.jsx';
import ElementType from '../../ElementType.jsx';
import { headlineByLevel } from '../../ElementType.jsx';
import BlockType from '../../markdown/BlockType.jsx';
import { headlineByLevel } from '../../markdown/BlockType.jsx';
import { isListItem } from '../../../stringFunctions.jsx';
//Detect headlines based on heights
@ -25,9 +25,9 @@ export default class DetectHeaders extends ToLineItemTransformation {
const height = item.height;
if (!item.type && height > min2ndLevelHeaderHeigthOnMaxPage) {
if (height == maxHeight) {
item.type = ElementType.H1;
item.type = BlockType.H1;
} else {
item.type = ElementType.H2;
item.type = BlockType.H2;
}
item.annotation = DETECTED_ANNOTATION;
detectedHeaders++;
@ -44,7 +44,7 @@ export default class DetectHeaders extends ToLineItemTransformation {
page.items.forEach(item => {
if (!item.type && item.height == range.max) {
item.annotation = DETECTED_ANNOTATION;
item.type = ElementType.enumValueOf(headlineType);
item.type = BlockType.enumValueOf(headlineType);
detectedHeaders++
}
});

8
src/javascript/models/transformations/textitem/DetectListItems.jsx
View File

@ -3,7 +3,7 @@ import ParseResult from '../../ParseResult.jsx';
import LineItem from '../../LineItem.jsx';
import Word from '../../Word.jsx';
import { REMOVED_ANNOTATION, ADDED_ANNOTATION, DETECTED_ANNOTATION } from '../../Annotation.jsx';
import ElementType from '../../ElementType.jsx';
import BlockType from '../../markdown/BlockType.jsx';
import { isListItemCharacter, isNumberedListItem } from '../../../stringFunctions.jsx';
//Detect items starting with -, •, etc...
@ -26,7 +26,7 @@ export default class DetectListItems extends ToLineItemTransformation {
foundListItems++
if (item.words[0].string === '-') {
item.annotation = DETECTED_ANNOTATION;
item.type = ElementType.LIST;
item.type = BlockType.LIST;
} else {
item.annotation = REMOVED_ANNOTATION;
const newWords = item.words.map(word => new Word({
@ -37,13 +37,13 @@ export default class DetectListItems extends ToLineItemTransformation {
...item,
words: newWords,
annotation: ADDED_ANNOTATION,
type: ElementType.LIST
type: BlockType.LIST
}));
}
} else if (isNumberedListItem(text)) { //TODO check that starts with 1 (kala chakra)
foundNumberedItems++;
item.annotation = DETECTED_ANNOTATION;
item.type = ElementType.LIST;
item.type = BlockType.LIST;
}
}
});

8
src/javascript/models/transformations/textitem/DetectTOC.jsx
View File

@ -4,8 +4,8 @@ import LineItem from '../../LineItem.jsx';
import Word from '../../Word.jsx';
import HeadlineFinder from '../../HeadlineFinder.jsx';
import { REMOVED_ANNOTATION, ADDED_ANNOTATION } from '../../Annotation.jsx';
import ElementType from '../../ElementType.jsx';
import { headlineByLevel } from '../../ElementType.jsx';
import BlockType from '../../markdown/BlockType.jsx';
import { headlineByLevel } from '../../markdown/BlockType.jsx';
import { isDigit, isNumber, wordMatch, hasOnly } from '../../../stringFunctions.jsx'
//Detect table of contents pages plus linked headlines
@ -90,7 +90,7 @@ export default class DetectTOC extends ToLineItemTransformation {
if (line === headlineItem) {
newBlocks.push(new LineItem({
...line,
type: ElementType.H2,
type: BlockType.H2,
annotation: ADDED_ANNOTATION
}));
}
@ -114,7 +114,7 @@ export default class DetectTOC extends ToLineItemTransformation {
words: [new Word({
string: ' '.repeat(tocLink.level * 3) + '-'
})].concat(tocLink.lineItem.words),
type: ElementType.TOC,
type: BlockType.TOC,
annotation: ADDED_ANNOTATION
}));
});

4
src/javascript/models/transformations/textitemblock/DetectCodeQuoteBlocks.jsx
View File

@ -1,7 +1,7 @@
import ToLineItemBlockTransformation from '../ToLineItemBlockTransformation.jsx';
import ParseResult from '../../ParseResult.jsx';
import { DETECTED_ANNOTATION } from '../../Annotation.jsx';
import ElementType from '../../ElementType.jsx';
import BlockType from '../../markdown/BlockType.jsx';
import { minXFromBlocks } from '../../../pageItemFunctions.jsx';
//Detect items which are code/quote blocks
@ -19,7 +19,7 @@ export default class DetectCodeQuoteBlocks extends ToLineItemBlockTransformation
page.items.forEach(block => {
if (!block.type && looksLikeCodeBlock(minX, block.items, mostUsedHeight)) {
block.annotation = DETECTED_ANNOTATION;
block.type = ElementType.CODE;
block.type = BlockType.CODE;
foundCodeItems++;
}
});

4
src/javascript/models/transformations/textitemblock/DetectListLevels.jsx
View File

@ -2,7 +2,7 @@ import ToLineItemBlockTransformation from '../ToLineItemBlockTransformation.jsx'
import ParseResult from '../../ParseResult.jsx';
import Word from '../../Word.jsx';
import { MODIFIED_ANNOTATION, UNCHANGED_ANNOTATION } from '../../Annotation.jsx';
import ElementType from '../../ElementType.jsx';
import BlockType from '../../markdown/BlockType.jsx';
// Cares for proper sub-item spacing/leveling
export default class DetectListLevels extends ToLineItemBlockTransformation {
@ -17,7 +17,7 @@ export default class DetectListLevels extends ToLineItemBlockTransformation {
var modifiedBlocks = 0;
parseResult.pages.forEach(page => {
page.items.filter(block => block.type === ElementType.LIST).forEach(listBlock => {
page.items.filter(block => block.type === BlockType.LIST).forEach(listBlock => {
var lastItemX;
var currentLevel = 0;
const xByLevel = {};