New Case Study:See how Anthropic automated 95% of dependency reviews with Socket.Learn More →
html-to-xlsx
Advanced tools
html-to-xlsx - npm Package Compare versions
Comparing version 1.0.2 to 1.1.0
@@ -8,337 +8,8 @@ 'use strict' | ||
| const tmpDir = require('os').tmpdir() | ||
| const excelbuilder = require('msexcel-builder-extended') | ||
| const XlsxPopulate = require('xlsx-populate') | ||
| const stylesMap = require('./stylesMap') | ||
| const tableToXlsx = require('./tableToXlsx') | ||
| const readFileAsync = util.promisify(fs.readFile) | ||
| const writeFileAsync = util.promisify(fs.writeFile) | ||
| function componentToHex (c) { | ||
| const hex = parseInt(c).toString(16) | ||
| return hex.length === 1 ? '0' + hex : hex | ||
| } | ||
| function rgbToHex (c) { | ||
| return componentToHex(c[0]) + componentToHex(c[1]) + componentToHex(c[2]) | ||
| } | ||
| function isColorDefined (c) { | ||
| return c[0] !== '0' || c[1] !== '0' || c[2] !== '0' || c[3] !== '0' | ||
| } | ||
| function getTotalCells (rows) { | ||
| let max = 0 | ||
| rows.forEach((row, idx) => { | ||
| let cellsCount = row.length | ||
| let maxRowSpan = 0 | ||
| const allCellsAreRowSpan = row.filter(c => c.rowspan > 1).length === row.length | ||
| maxRowSpan = row.reduce((acu, cell) => { | ||
| if (cell.rowspan && cell.rowspan > acu) { | ||
| acu = cell.rowspan | ||
| } | ||
| return acu | ||
| }, 0) | ||
| row.forEach((cell) => { | ||
| if (cell.colspan && cell.colspan > 1) { | ||
| cellsCount += (cell.colspan) - 1 | ||
| } | ||
| }) | ||
| if (maxRowSpan > 1 && (row.length === 1 || allCellsAreRowSpan)) { | ||
| const rowsToMerge = maxRowSpan - 1 | ||
| let mergedMaxCells = 0 | ||
| for (let i = 0; i < rowsToMerge; i++) { | ||
| const nextRowIndex = idx + (i + 1) | ||
| if (rows[nextRowIndex] == null) { | ||
| continue | ||
| } | ||
| if (rows[nextRowIndex].length > mergedMaxCells) { | ||
| mergedMaxCells = rows[nextRowIndex].length | ||
| } | ||
| } | ||
| cellsCount += mergedMaxCells | ||
| } | ||
| if (cellsCount > max) { | ||
| max = cellsCount | ||
| } | ||
| }) | ||
| return max | ||
| } | ||
| function getTotalRows (rows) { | ||
| let rowCount = 0 | ||
| let rowsToMerge = 0 | ||
| rows.forEach((row) => { | ||
| let maxRowSpan = 0 | ||
| const allCellsAreRowSpan = row.filter(c => c.rowspan > 1).length === row.length | ||
| maxRowSpan = row.reduce((acu, cell) => { | ||
| if (cell.rowspan && cell.rowspan > acu) { | ||
| acu = cell.rowspan | ||
| } | ||
| return acu | ||
| }, 0) | ||
| if (rowsToMerge > 0) { | ||
| rowsToMerge-- | ||
| } else { | ||
| if (maxRowSpan > 1) { | ||
| rowsToMerge += maxRowSpan - 1 | ||
| rowCount += rowsToMerge | ||
| if (row.length > 1 && !allCellsAreRowSpan) { | ||
| rowCount++ | ||
| } | ||
| } else { | ||
| rowCount++ | ||
| } | ||
| } | ||
| }) | ||
| return rowCount | ||
| } | ||
| function getBorderStyle (border) { | ||
| if (border === 'none') return undefined | ||
| if (border === 'solid') return 'thin' | ||
| if (border === 'double') return 'double' | ||
| return undefined | ||
| } | ||
| function tableToXlsx (options, table, id, cb) { | ||
| const workbook = excelbuilder.createWorkbook( | ||
| options.tmpDir, | ||
| `${id}.xlsx`, | ||
| options | ||
| ) | ||
| const totalCells = getTotalCells(table.rows) | ||
| const totalRows = getTotalRows(table.rows) | ||
| const sheet1 = workbook.createSheet( | ||
| 'sheet1', | ||
| totalCells, | ||
| totalRows | ||
| ) | ||
| const maxWidths = [] | ||
| let currRow = 0 | ||
| let rowsToMerge = 0 | ||
| let rowOffset = [] | ||
| for (let i = 0; i < table.rows.length; i++) { | ||
| // set at the row level column offsets and column position | ||
| let maxHeight = 0 | ||
| let maxRowSpan = 0 | ||
| const tmpOffsets = [] | ||
| let currCol = 0 | ||
| let colOffset = 0 | ||
| let tmpCol = 0 | ||
| let mergedRow = false | ||
| const cellsCount = table.rows[i].length | ||
| const allCellsAreRowSpan = table.rows[i].filter(c => c.rowspan > 1).length === cellsCount | ||
| if (rowsToMerge > 0) { | ||
| mergedRow = true | ||
| currRow-- | ||
| rowsToMerge-- | ||
| } | ||
| // clean out offsets that are no longer valid | ||
| rowOffset = rowOffset.filter((offset) => { | ||
| // eslint-disable-next-line no-unneeded-ternary | ||
| return offset.stop <= currRow ? false : true | ||
| }) | ||
| // Is the current column in the offset list? | ||
| rowOffset.forEach((item) => { | ||
| // if so add an offset to shift the column start | ||
| if (currRow <= item.stop) { | ||
| colOffset += item.colOffset || 1 | ||
| } | ||
| }) | ||
| let cell | ||
| // column iterator | ||
| for (let j = 0; j < table.rows[i].length; j++) { | ||
| cell = table.rows[i][j] | ||
| // On the start of each row, reset the column counters | ||
| // Use tmpCol to manipulate the column value | ||
| currCol = j === 0 ? 1 : currCol + 1 | ||
| tmpCol = currCol + colOffset | ||
| // don't take into account height of merged cells (rowspan) for max height. | ||
| // this is the behavior of browsers too when rendering tables. | ||
| // see issue #20 for more info | ||
| if (cell.height > maxHeight && (cell.rowspan == null || cell.rowspan <= 1)) { | ||
| maxHeight = cell.height | ||
| } | ||
| // don't take into account width of merged cells for max width, | ||
| // and don't apply width for merged cells. | ||
| // this is the behavior of browsers too when rendering tables. | ||
| // see issue #19, #24 for more info | ||
| if (cell.colspan == null || cell.colspan <= 1) { | ||
| if (cell.width > (maxWidths[j] || 0)) { | ||
| sheet1.width(currCol, cell.width / 7) | ||
| maxWidths[j] = cell.width | ||
| } | ||
| } | ||
| sheet1.set( | ||
| tmpCol, | ||
| currRow + 1, | ||
| cell.value | ||
| ? cell.value.replace(/&(?!amp;)/g, '&').replace(/&(?!amp;)/g, '&') | ||
| : cell.value | ||
| ) | ||
| sheet1.align(tmpCol, currRow + 1, cell.horizontalAlign) | ||
| sheet1.valign( | ||
| tmpCol, | ||
| currRow + 1, | ||
| cell.verticalAlign === 'middle' ? 'center' : cell.verticalAlign | ||
| ) | ||
| sheet1.wrap(tmpCol, currRow + 1, cell.wrapText === 'scroll') | ||
| if (isColorDefined(cell.backgroundColor)) { | ||
| sheet1.fill(tmpCol, currRow + 1, { | ||
| type: 'solid', | ||
| fgColor: 'FF' + rgbToHex(cell.backgroundColor), | ||
| bgColor: '64' | ||
| }) | ||
| } | ||
| sheet1.font(tmpCol, currRow + 1, { | ||
| family: '3', | ||
| scheme: 'minor', | ||
| sz: parseInt(cell.fontSize.replace('px', '')) * 18 / 24, | ||
| bold: | ||
| cell.fontWeight === 'bold' || parseInt(cell.fontWeight, 10) >= 700, | ||
| color: isColorDefined(cell.foregroundColor) | ||
| ? 'FF' + rgbToHex(cell.foregroundColor) | ||
| : undefined | ||
| }) | ||
| sheet1.border(tmpCol, currRow + 1, { | ||
| left: getBorderStyle(cell.border.left), | ||
| top: getBorderStyle(cell.border.top), | ||
| right: getBorderStyle(cell.border.right), | ||
| bottom: getBorderStyle(cell.border.bottom) | ||
| }) | ||
| // Now that we have done all of the formatting to the cell, see if the row needs merged. | ||
| // Note that calling merge twice on the same cell causes Excel to be unreadable. | ||
| if (cell.rowspan > 1) { | ||
| // address colspan at the same time as rowspan | ||
| let coloffset = cell.colspan > 1 ? cell.colspan - 1 : 0 | ||
| let endRow = (currRow + cell.rowspan) - ((cellsCount === 1 || allCellsAreRowSpan) ? 1 : 0) | ||
| sheet1.merge( | ||
| { col: tmpCol, row: currRow + 1 }, | ||
| { col: tmpCol + coloffset, row: endRow } | ||
| ) | ||
| // store the rowspan for later use to shift over the column starting point | ||
| tmpOffsets.push({ | ||
| col: tmpCol, | ||
| stop: endRow, | ||
| colOffset: cell.colspan | ||
| }) | ||
| currCol += cell.colspan - 1 | ||
| for (let k = currRow + 1; k <= cell.rowspan; k++) { | ||
| sheet1.border(k + 1, currRow + cell.colspan, { | ||
| left: getBorderStyle(cell.border.left), | ||
| top: getBorderStyle(cell.border.top), | ||
| right: getBorderStyle(cell.border.right), | ||
| bottom: getBorderStyle(cell.border.bottom) | ||
| }) | ||
| } | ||
| if (cell.rowspan > maxRowSpan) { | ||
| maxRowSpan = cell.rowspan | ||
| } | ||
| } | ||
| // If we already did rowspan, we did the colspan at the same time so this only does colspan. | ||
| // No need to store the colspan as that doesn't carry over to another row | ||
| if (cell.colspan > 1 && cell.rowspan === 1) { | ||
| let coloffset = cell.colspan > 1 ? cell.colspan - 1 : 0 | ||
| sheet1.merge( | ||
| { col: tmpCol, row: currRow + 1 }, | ||
| { col: tmpCol + coloffset, row: currRow + 1 } | ||
| ) | ||
| currCol += cell.colspan - 1 | ||
| for (let k = tmpCol; k <= cell.colspan; k++) { | ||
| sheet1.border(k + 1, currRow + 1, { | ||
| left: getBorderStyle(cell.border.left), | ||
| top: getBorderStyle(cell.border.top), | ||
| right: getBorderStyle(cell.border.right), | ||
| bottom: getBorderStyle(cell.border.bottom) | ||
| }) | ||
| } | ||
| } | ||
| } | ||
| sheet1.height(currRow + 1, maxHeight * 18 / 24) | ||
| if (!cell) { | ||
| throw new Error( | ||
| 'Cell not found, make sure there are td elements inside tr' | ||
| ) | ||
| } | ||
| if (mergedRow && rowsToMerge > 0) { | ||
| // if row was merged one we restore its index | ||
| currRow += 1 | ||
| } | ||
| currRow += 1 | ||
| if (maxRowSpan > 1) { | ||
| rowsToMerge = maxRowSpan - 1 | ||
| if (cellsCount > 1 && !allCellsAreRowSpan) { | ||
| currRow++ | ||
| } | ||
| } | ||
| rowOffset = rowOffset.concat(tmpOffsets) | ||
| } | ||
| return new Promise((resolve, reject) => { | ||
| workbook.save((err) => { | ||
| if (err) { | ||
| return reject(err) | ||
| } | ||
| resolve( | ||
| fs.createReadStream(path.join(options.tmpDir, `${id}.xlsx`)) | ||
| ) | ||
| }) | ||
| }) | ||
| } | ||
| module.exports = (opt = {}) => { | ||
@@ -377,3 +48,3 @@ const options = { ...opt } | ||
| const table = await currentExtractFn({ | ||
| const tables = await currentExtractFn({ | ||
| ...convertOptions, | ||
@@ -385,4 +56,10 @@ html: htmlPath, | ||
| const stream = await tableToXlsx(options, table, id) | ||
| let stream | ||
| if (!tables || (Array.isArray(tables) && tables.length === 0)) { | ||
| throw new Error('No table element(s) found in html') | ||
| } | ||
| stream = await tableToXlsx(options, tables, id) | ||
| return stream | ||
@@ -393,1 +70,7 @@ } | ||
| } | ||
| module.exports.getXlsxStyleNames = () => { | ||
| return Object.keys(stylesMap) | ||
| } | ||
| module.exports.XlsxPopulate = XlsxPopulate |
| // eslint-disable-next-line no-unused-vars | ||
| function conversion () { | ||
| var tableOut = { rows: [] } | ||
| var table = document.querySelector('table') | ||
| var tables = document.querySelectorAll('table') | ||
| var tablesOutput = [] | ||
| var i | ||
| if (!table) { | ||
| return tableOut | ||
| if (tables.length === 0) { | ||
| return tablesOutput | ||
| } | ||
| for (var r = 0, n = table.rows.length; r < n; r++) { | ||
| var row = [] | ||
| tableOut.rows.push(row) | ||
| for (i = 0; i < tables.length; i++) { | ||
| var table = tables[i] | ||
| var tableOut = { rows: [] } | ||
| var nameAttr = table.getAttribute('name') | ||
| var dataSheetName = table.dataset.sheetName | ||
| var dataIgnoreName = table.dataset.ignoreSheetName | ||
| for (var c = 0, m = table.rows[r].cells.length; c < m; c++) { | ||
| var cell = table.rows[r].cells[c] | ||
| var cs = document.defaultView.getComputedStyle(cell, null) | ||
| if (dataIgnoreName == null) { | ||
| if (dataSheetName != null) { | ||
| tableOut.name = dataSheetName | ||
| } else if (nameAttr != null) { | ||
| tableOut.name = nameAttr | ||
| } | ||
| } | ||
| row.push({ | ||
| value: cell.innerHTML, | ||
| backgroundColor: cs.getPropertyValue('background-color').match(/\d+/g), | ||
| foregroundColor: cs.getPropertyValue('color').match(/\d+/g), | ||
| fontSize: cs.getPropertyValue('font-size'), | ||
| fontWeight: cs.getPropertyValue('font-weight'), | ||
| verticalAlign: cs.getPropertyValue('vertical-align'), | ||
| horizontalAlign: cs.getPropertyValue('text-align'), | ||
| wrapText: cs.getPropertyValue('overflow'), | ||
| width: cell.clientWidth, | ||
| height: cell.clientHeight, | ||
| rowspan: cell.rowSpan, | ||
| colspan: cell.colSpan, | ||
| border: { | ||
| top: cs.getPropertyValue('border-top-style'), | ||
| right: cs.getPropertyValue('border-right-style'), | ||
| bottom: cs.getPropertyValue('border-bottom-style'), | ||
| left: cs.getPropertyValue('border-left-style'), | ||
| width: cs.getPropertyValue('border-width-style') | ||
| } | ||
| }) | ||
| for (var r = 0, n = table.rows.length; r < n; r++) { | ||
| var row = [] | ||
| tableOut.rows.push(row) | ||
| for (var c = 0, m = table.rows[r].cells.length; c < m; c++) { | ||
| var cell = table.rows[r].cells[c] | ||
| var cs = document.defaultView.getComputedStyle(cell, null) | ||
| var type = cell.dataset.cellType != null && cell.dataset.cellType !== '' ? cell.dataset.cellType.toLowerCase() : undefined | ||
| var formatStr = cell.dataset.cellFormatStr != null ? cell.dataset.cellFormatStr : undefined | ||
| var formatEnum = cell.dataset.cellFormatEnum != null && !isNaN(parseInt(cell.dataset.cellFormatEnum, 10)) ? parseInt(cell.dataset.cellFormatEnum, 10) : undefined | ||
| row.push({ | ||
| type: type, | ||
| // returns the html inside the td element with special html characters like "&" escaped to & | ||
| value: cell.innerHTML, | ||
| // returns just the real text inside the td element with special html characters like "&" left as it is | ||
| valueText: cell.innerText, | ||
| formatStr: formatStr, | ||
| formatEnum: formatEnum, | ||
| backgroundColor: cs.getPropertyValue('background-color').match(/\d+/g), | ||
| foregroundColor: cs.getPropertyValue('color').match(/\d+/g), | ||
| fontFamily: cs.getPropertyValue('font-family').replace(/["']/g, ''), | ||
| fontSize: cs.getPropertyValue('font-size'), | ||
| fontStyle: cs.getPropertyValue('font-style'), | ||
| fontWeight: cs.getPropertyValue('font-weight'), | ||
| textDecoration: { | ||
| line: cs.getPropertyValue('text-decoration').split(' ')[0] | ||
| }, | ||
| verticalAlign: cs.getPropertyValue('vertical-align'), | ||
| horizontalAlign: cs.getPropertyValue('text-align'), | ||
| wrapText: cs.getPropertyValue('overflow'), | ||
| width: cell.clientWidth, | ||
| height: cell.clientHeight, | ||
| rowspan: cell.rowSpan, | ||
| colspan: cell.colSpan, | ||
| border: { | ||
| top: cs.getPropertyValue('border-top-style'), | ||
| topColor: cs.getPropertyValue('border-top-color').match(/\d+/g), | ||
| topStyle: cs.getPropertyValue('border-top-style'), | ||
| topWidth: cs.getPropertyValue('border-top-width'), | ||
| right: cs.getPropertyValue('border-right-style'), | ||
| rightColor: cs.getPropertyValue('border-right-color').match(/\d+/g), | ||
| rightStyle: cs.getPropertyValue('border-right-style'), | ||
| rightWidth: cs.getPropertyValue('border-right-width'), | ||
| bottom: cs.getPropertyValue('border-bottom-style'), | ||
| bottomColor: cs.getPropertyValue('border-bottom-color').match(/\d+/g), | ||
| bottomStyle: cs.getPropertyValue('border-bottom-style'), | ||
| bottomWidth: cs.getPropertyValue('border-bottom-width'), | ||
| left: cs.getPropertyValue('border-left-style'), | ||
| leftColor: cs.getPropertyValue('border-left-color').match(/\d+/g), | ||
| leftStyle: cs.getPropertyValue('border-left-style'), | ||
| leftWidth: cs.getPropertyValue('border-left-width') | ||
| } | ||
| }) | ||
| } | ||
| } | ||
| tablesOutput.push(tableOut) | ||
| } | ||
| return tableOut | ||
| if (tablesOutput.length === 1) { | ||
| return tablesOutput[0] | ||
| } | ||
| return tablesOutput | ||
| } |
| { | ||
| "name": "html-to-xlsx", | ||
| "version": "1.0.2", | ||
| "version": "1.1.0", | ||
| "author": { | ||
@@ -35,14 +35,16 @@ "name": "Jan Blaha", | ||
| "dependencies": { | ||
| "msexcel-builder-extended": "0.0.8", | ||
| "uuid": "3.2.1" | ||
| "moment": "2.22.1", | ||
| "tinycolor2": "1.4.1", | ||
| "uuid": "3.2.1", | ||
| "xlsx-populate": "1.18.0" | ||
| }, | ||
| "devDependencies": { | ||
| "babel-eslint": "8.2.2", | ||
| "chrome-page-eval": "1.0.0", | ||
| "chrome-page-eval": "1.2.0", | ||
| "eslint": "4.18.2", | ||
| "eslint-plugin-babel": "4.1.2", | ||
| "mocha": "5.0.2", | ||
| "phantom-page-eval": "1.0.1", | ||
| "phantom-page-eval": "1.2.0", | ||
| "phantomjs": "1.9.17", | ||
| "puppeteer": "1.0.0", | ||
| "puppeteer": "1.11.0", | ||
| "should": "13.2.1", | ||
@@ -53,4 +55,4 @@ "standard": "11.0.0", | ||
| "scripts": { | ||
| "test": "mocha --timeout 10000 test/test.js && standard" | ||
| "test": "mocha --timeout 15000 test/test.js && standard" | ||
| } | ||
| } |
822
test/test.js
@@ -29,36 +29,2 @@ const should = require('should') | ||
| async function createHtmlFile (html) { | ||
| const outputPath = path.join(tmpDir, `${uuid()}.html`) | ||
| await writeFileAsync(outputPath, html) | ||
| return outputPath | ||
| } | ||
| function rmDir (dirPath) { | ||
| if (!fs.existsSync(dirPath)) { | ||
| fs.mkdirSync(dirPath) | ||
| } | ||
| let files | ||
| try { | ||
| files = fs.readdirSync(dirPath) | ||
| } catch (e) { | ||
| return | ||
| } | ||
| if (files.length > 0) { | ||
| for (let i = 0; i < files.length; i++) { | ||
| let filePath = `${dirPath}/${files[i]}` | ||
| try { | ||
| if (fs.statSync(filePath).isFile()) { | ||
| fs.unlinkSync(filePath) | ||
| } | ||
| } catch (e) { } | ||
| } | ||
| } | ||
| } | ||
| describe('html extraction', () => { | ||
@@ -78,5 +44,11 @@ beforeEach(() => { | ||
| function common (pageEval) { | ||
| it('should build simple table', async () => { | ||
| it('should parse simple table', async () => { | ||
| const table = await pageEval({ | ||
| html: await createHtmlFile(`<table><tr><td>1</td></tr></table>`), | ||
| html: await createHtmlFile(` | ||
| <table> | ||
| <tr> | ||
| <td>1</td> | ||
| </tr> | ||
| </table> | ||
| `), | ||
| scriptFn: extractTableScriptFn | ||
@@ -90,2 +62,79 @@ }) | ||
| it('should parse value', async () => { | ||
| const table = await pageEval({ | ||
| html: await createHtmlFile(` | ||
| <table> | ||
| <tr> | ||
| <td>node.js & javascript</td> | ||
| </tr> | ||
| </table> | ||
| `), | ||
| scriptFn: extractTableScriptFn | ||
| }) | ||
| table.rows.should.have.length(1) | ||
| table.rows[0].should.have.length(1) | ||
| table.rows[0][0].value.should.be.eql('node.js & javascript') | ||
| }) | ||
| it('should parse un-escaped value', async () => { | ||
| const table = await pageEval({ | ||
| html: await createHtmlFile(` | ||
| <table> | ||
| <tr> | ||
| <td>node.js & javascript</td> | ||
| </tr> | ||
| </table> | ||
| `), | ||
| scriptFn: extractTableScriptFn | ||
| }) | ||
| table.rows.should.have.length(1) | ||
| table.rows[0].should.have.length(1) | ||
| table.rows[0][0].valueText.should.be.eql('node.js & javascript') | ||
| }) | ||
| it('should parse cell data type', async () => { | ||
| const table = await pageEval({ | ||
| html: await createHtmlFile(` | ||
| <table> | ||
| <tr> | ||
| <td data-cell-type="number">10</td> | ||
| <td data-cell-type="boolean">1</td> | ||
| <td data-cell-type="date">2019-01-22</td> | ||
| <td data-cell-type="datetime">2019-01-22T17:31:36.242Z</td> | ||
| <td data-cell-type="formula">=SUM(A1, B1)</td> | ||
| </tr> | ||
| </table> | ||
| `), | ||
| scriptFn: extractTableScriptFn | ||
| }) | ||
| table.rows.should.have.length(1) | ||
| table.rows[0].should.have.length(5) | ||
| table.rows[0][0].type = 'number' | ||
| table.rows[0][1].type = 'boolean' | ||
| table.rows[0][2].type = 'date' | ||
| table.rows[0][3].type = 'datetime' | ||
| table.rows[0][4].type = 'formula' | ||
| }) | ||
| it('should parse format str and enum', async () => { | ||
| const table = await pageEval({ | ||
| html: await createHtmlFile(` | ||
| <table> | ||
| <tr> | ||
| <td data-cell-type="number" data-cell-format-str="0.00">10</td> | ||
| <td data-cell-type="number" data-cell-format-enum="3">100000</td> | ||
| </tr> | ||
| </table> | ||
| `), | ||
| scriptFn: extractTableScriptFn | ||
| }) | ||
| table.rows.should.have.length(1) | ||
| table.rows[0][0].formatStr = '0.00' | ||
| table.rows[0][1].formatEnum = 3 | ||
| }) | ||
| it('should parse background color', async () => { | ||
@@ -109,2 +158,19 @@ const table = await pageEval({ | ||
| it('should parse fontFamily', async () => { | ||
| const table = await pageEval({ | ||
| html: await createHtmlFile(` | ||
| <table> | ||
| <tr> | ||
| <td style='font-family:Calibri'>1</td> | ||
| <td style='font-family: "Times New Roman"'>2</td> | ||
| </tr> | ||
| </table> | ||
| `), | ||
| scriptFn: extractTableScriptFn | ||
| }) | ||
| table.rows[0][0].fontFamily.should.be.eql('Calibri') | ||
| table.rows[0][1].fontFamily.should.be.eql('Times New Roman') | ||
| }) | ||
| it('should parse fontsize', async () => { | ||
@@ -157,3 +223,9 @@ const table = await pageEval({ | ||
| const table = await pageEval({ | ||
| html: await createHtmlFile(`<table><tr><td style='border-style:solid;'>1</td></tr></table>`), | ||
| html: await createHtmlFile(` | ||
| <table> | ||
| <tr> | ||
| <td style='border-style:solid;'>1</td> | ||
| </tr> | ||
| </table> | ||
| `), | ||
| scriptFn: extractTableScriptFn | ||
@@ -168,2 +240,19 @@ }) | ||
| it('should parse complex border', async () => { | ||
| const table = await pageEval({ | ||
| html: await createHtmlFile(` | ||
| <table> | ||
| <tr> | ||
| <td style='border-left: 1px solid red;'>1</td> | ||
| </tr> | ||
| </table> | ||
| `), | ||
| scriptFn: extractTableScriptFn | ||
| }) | ||
| table.rows[0][0].border.leftColor.should.be.eql(['255', '0', '0']) | ||
| table.rows[0][0].border.leftWidth.should.be.eql('1px') | ||
| table.rows[0][0].border.leftStyle.should.be.eql('solid') | ||
| }) | ||
| it('should parse overflow', async () => { | ||
@@ -178,2 +267,19 @@ const table = await pageEval({ | ||
| it('should parse textDecoration', async () => { | ||
| const table = await pageEval({ | ||
| html: await createHtmlFile(` | ||
| <table> | ||
| <tr> | ||
| <td style='text-decoration: underline'> | ||
| 1234 | ||
| </td> | ||
| </tr> | ||
| </table> | ||
| `), | ||
| scriptFn: extractTableScriptFn | ||
| }) | ||
| table.rows[0][0].textDecoration.line.should.be.eql('underline') | ||
| }) | ||
| it('should parse backgroud color from styles with line endings', async () => { | ||
@@ -189,4 +295,2 @@ const table = await pageEval({ | ||
| it('should work for long tables', async function () { | ||
| this.timeout(7000) | ||
| let rows = '' | ||
@@ -232,8 +336,11 @@ | ||
| <tr> | ||
| <td rowspan='3'>Row 1 Col 1</td><td>Row 1 Col 2</td> | ||
| <td>Row 1 Col 3</td><td>Row 1 Col 4</td> | ||
| <td rowspan='3'>Row 1 Col 1</td> | ||
| <td>Row 1 Col 2</td> | ||
| <td>Row 1 Col 3</td> | ||
| <td>Row 1 Col 4</td> | ||
| </tr> | ||
| <tr> | ||
| <td rowspan='2'>Row 2 Col 1</td> | ||
| <td rowspan='2'>Row 2 Col 2</td><td>Row 2 Col 3</td> | ||
| <td rowspan='2'>Row 2 Col 2</td> | ||
| <td>Row 2 Col 3</td> | ||
| </tr> | ||
@@ -252,2 +359,26 @@ <tr> | ||
| }) | ||
| it('should parse th elements', async () => { | ||
| const table = await pageEval({ | ||
| html: await createHtmlFile(` | ||
| <table> | ||
| <tr> | ||
| <th>col1</th> | ||
| <th>col2</th> | ||
| </tr> | ||
| <tr> | ||
| <td>1</td> | ||
| <td>2</td> | ||
| </tr> | ||
| </table> | ||
| `), | ||
| scriptFn: extractTableScriptFn | ||
| }) | ||
| table.rows.should.have.length(2) | ||
| table.rows[0][0].value.should.be.eql('col1') | ||
| table.rows[0][1].value.should.be.eql('col2') | ||
| table.rows[1][0].value.should.be.eql('1') | ||
| table.rows[1][1].value.should.be.eql('2') | ||
| }) | ||
| } | ||
@@ -277,3 +408,9 @@ }) | ||
| it('should not fail', async () => { | ||
| const stream = await conversion('<table><tr><td>hello</td></tr>') | ||
| const stream = await conversion(` | ||
| <table> | ||
| <tr> | ||
| <td>hello</td> | ||
| </tr> | ||
| </table | ||
| `) | ||
@@ -283,4 +420,170 @@ stream.should.have.property('readable') | ||
| it('default sheet name should be Sheet1', async () => { | ||
| const stream = await conversion(` | ||
| <table> | ||
| <tr> | ||
| <td>hello</td> | ||
| </tr> | ||
| </table | ||
| `) | ||
| const parsedXlsx = await new Promise((resolve, reject) => { | ||
| const bufs = [] | ||
| stream.on('error', reject) | ||
| stream.on('data', (d) => { bufs.push(d) }) | ||
| stream.on('end', () => { | ||
| const buf = Buffer.concat(bufs) | ||
| resolve(xlsx.read(buf)) | ||
| }) | ||
| }) | ||
| should(parsedXlsx.SheetNames[0]).be.eql('Sheet1') | ||
| }) | ||
| it('shoule be able to set custom sheet name', async () => { | ||
| const parseXlsx = (xlsxStream) => { | ||
| return new Promise((resolve, reject) => { | ||
| const bufs = [] | ||
| xlsxStream.on('error', reject) | ||
| xlsxStream.on('data', (d) => { bufs.push(d) }) | ||
| xlsxStream.on('end', () => { | ||
| const buf = Buffer.concat(bufs) | ||
| resolve(xlsx.read(buf)) | ||
| }) | ||
| }) | ||
| } | ||
| let stream = await conversion(` | ||
| <table name="custom"> | ||
| <tr> | ||
| <td>1</td> | ||
| </tr> | ||
| </table> | ||
| `) | ||
| let parsedXlsx = await parseXlsx(stream) | ||
| should(parsedXlsx.SheetNames[0]).be.eql('custom') | ||
| stream = await conversion(` | ||
| <table data-sheet-name="custom2"> | ||
| <tr> | ||
| <td>1</td> | ||
| </tr> | ||
| </table> | ||
| `) | ||
| parsedXlsx = await parseXlsx(stream) | ||
| should(parsedXlsx.SheetNames[0]).be.eql('custom2') | ||
| }) | ||
| it('should be able to set cell with datatypes', async () => { | ||
| const stream = await conversion(` | ||
| <table> | ||
| <tr> | ||
| <td data-cell-type="number">10</td> | ||
| <td data-cell-type="number">10</td> | ||
| <td data-cell-type="boolean">1</td> | ||
| <td data-cell-type="date">2019-01-22</td> | ||
| <td data-cell-type="datetime">2019-01-22T17:31:36.000-05:00</td> | ||
| <td data-cell-type="formula">=SUM(A1, B1)</td> | ||
| </tr> | ||
| </table> | ||
| `) | ||
| const parsedXlsx = await new Promise((resolve, reject) => { | ||
| const bufs = [] | ||
| stream.on('error', reject) | ||
| stream.on('data', (d) => { bufs.push(d) }) | ||
| stream.on('end', () => { | ||
| const buf = Buffer.concat(bufs) | ||
| resolve(xlsx.read(buf)) | ||
| }) | ||
| }) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A1'].v).be.eql(10) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['B1'].v).be.eql(10) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['C1'].v).be.eql(true) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['D1'].v).be.Number() | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['E1'].v).be.Number() | ||
| }) | ||
| it('should be able to set cell format', async () => { | ||
| const stream = await conversion(` | ||
| <table> | ||
| <tr> | ||
| <td data-cell-type="number" data-cell-format-str="0.00">10</td> | ||
| <td data-cell-type="number" data-cell-format-enum="3">100000</td> | ||
| </tr> | ||
| </table> | ||
| `) | ||
| const parsedXlsx = await new Promise((resolve, reject) => { | ||
| const bufs = [] | ||
| stream.on('error', reject) | ||
| stream.on('data', (d) => { bufs.push(d) }) | ||
| stream.on('end', () => { | ||
| const buf = Buffer.concat(bufs) | ||
| resolve(xlsx.read(buf)) | ||
| }) | ||
| }) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A1'].v).be.eql(10) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A1'].w).be.eql('10.00') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['B1'].v).be.eql(100000) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['B1'].w).be.eql('100,000') | ||
| }) | ||
| it('should work with th elements', async () => { | ||
| const stream = await conversion(` | ||
| <table> | ||
| <tr> | ||
| <th>col1</th> | ||
| <th>col2</th> | ||
| </tr> | ||
| <tr> | ||
| <td>1</td> | ||
| <td>2</td> | ||
| </tr> | ||
| </table> | ||
| `) | ||
| const parsedXlsx = await new Promise((resolve, reject) => { | ||
| const bufs = [] | ||
| stream.on('error', reject) | ||
| stream.on('data', (d) => { bufs.push(d) }) | ||
| stream.on('end', () => { | ||
| const buf = Buffer.concat(bufs) | ||
| resolve(xlsx.read(buf)) | ||
| }) | ||
| }) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A1'].v).be.eql('col1') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['B1'].v).be.eql('col2') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A2'].v).be.eql('1') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['B2'].v).be.eql('2') | ||
| }) | ||
| it('should not fail when last cell of a row has rowspan', async () => { | ||
| const stream = await conversion(`<table><tr><td rowspan="2">Cell RowSpan</td></tr><tr><td>Foo</td></tr></table>`) | ||
| const stream = await conversion(` | ||
| <table> | ||
| <tr> | ||
| <td rowspan="2">Cell RowSpan</td> | ||
| </tr> | ||
| <tr> | ||
| <td>Foo</td> | ||
| </tr> | ||
| </table> | ||
| `) | ||
@@ -290,3 +593,3 @@ stream.should.have.property('readable') | ||
| it('should work when using special rowspan layout #1', async () => { | ||
| it('should work when using special rowspan layout #1 (row with just one cell)', async () => { | ||
| const stream = await conversion(` | ||
@@ -326,5 +629,10 @@ <table> | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['C2'].v).be.eql('World') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.c).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.r).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.c).be.eql(0) | ||
| }) | ||
| it('should work when using special rowspan layout #2', async () => { | ||
| it('should work when using special rowspan layout #2 (row with just one cell, more rows)', async () => { | ||
| const stream = await conversion(` | ||
@@ -334,2 +642,50 @@ <table> | ||
| <td rowspan="3">ROWSPAN 3</td> | ||
| </tr> | ||
| <tr> | ||
| <td>Ipsum</td> | ||
| <td>Data</td> | ||
| </tr> | ||
| <tr> | ||
| <td>Hello</td> | ||
| <td>World</td> | ||
| </tr> | ||
| <tr> | ||
| <td>Something</td> | ||
| <td>Else</td> | ||
| </tr> | ||
| </table> | ||
| `) | ||
| const parsedXlsx = await new Promise((resolve, reject) => { | ||
| const bufs = [] | ||
| stream.on('error', reject) | ||
| stream.on('data', (d) => { bufs.push(d) }) | ||
| stream.on('end', () => { | ||
| const buf = Buffer.concat(bufs) | ||
| resolve(xlsx.read(buf)) | ||
| }) | ||
| }) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A1'].v).be.eql('ROWSPAN 3') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A2']).be.undefined() | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['B1'].v).be.eql('Ipsum') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['C1'].v).be.eql('Data') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['B2'].v).be.eql('Hello') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['C2'].v).be.eql('World') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A3'].v).be.eql('Something') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['B3'].v).be.eql('Else') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.c).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.r).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.c).be.eql(0) | ||
| }) | ||
| it('should work when using special rowspan layout #3 (row with normal cells and first cell with rowspan)', async () => { | ||
| const stream = await conversion(` | ||
| <table> | ||
| <tr> | ||
| <td rowspan="3">ROWSPAN 3</td> | ||
| <td>Header 2</td> | ||
@@ -370,5 +726,10 @@ <td>Header 3</td> | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['C3'].v).be.eql('World') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.c).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.r).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.c).be.eql(0) | ||
| }) | ||
| it('should work when using special rowspan layout #3', async () => { | ||
| it('should work when using special rowspan layout #4 (row with all cells using rowspan)', async () => { | ||
| const stream = await conversion(` | ||
@@ -413,5 +774,25 @@ <table> | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['E2'].v).be.eql('Doc2.') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.c).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.r).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.c).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].s.c).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].e.r).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].e.c).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].s.c).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].e.r).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].e.c).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][3].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][3].s.c).be.eql(3) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][3].e.r).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][3].e.c).be.eql(3) | ||
| }) | ||
| it('should work when using special rowspan layout #4', async () => { | ||
| it('should work when using special rowspan layout #5 (row with lot of cells using rowspan but last one without it)', async () => { | ||
| const stream = await conversion(` | ||
@@ -458,5 +839,20 @@ <table> | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['D3'].v).be.eql('Doc2.') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.c).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.r).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.c).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].s.c).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].e.r).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].e.c).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].s.c).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].e.r).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].e.c).be.eql(2) | ||
| }) | ||
| it('should work when using special rowspan layout #5', async () => { | ||
| it('should work when using special rowspan layout #6 (row with lot of cells using rowspan but last one using colspan)', async () => { | ||
| const stream = await conversion(` | ||
@@ -508,5 +904,30 @@ <table> | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['D3'].v).be.eql('Text3') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.c).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.r).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.c).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].s.c).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].e.r).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].e.c).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].s.c).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].e.r).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].e.c).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][3].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][3].s.c).be.eql(3) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][3].e.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][3].e.c).be.eql(5) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][4].s.r).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][4].s.c).be.eql(4) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][4].e.r).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][4].e.c).be.eql(5) | ||
| }) | ||
| it('should work when using special rowspan layout #6', async () => { | ||
| it('should work when using special rowspan layout #7 (row with only one cell that uses rowspan greater than available rows)', async () => { | ||
| const stream = await conversion(` | ||
@@ -534,5 +955,6 @@ <table> | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A2']).be.undefined() | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges']).be.undefined() | ||
| }) | ||
| it('should work when using special rowspan layout #7', async () => { | ||
| it('should work when using special rowspan layout #8 (complex calendar like layout)', async () => { | ||
| const stream = await conversion(` | ||
@@ -683,7 +1105,245 @@ <table border="1" style="border-collapse:collapse;"> | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['Q4'].v).be.eql('22') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.c).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.r).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.c).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].s.c).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].e.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].e.c).be.eql(6) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].s.c).be.eql(7) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].e.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][2].e.c).be.eql(11) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][3].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][3].s.c).be.eql(12) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][3].e.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][3].e.c).be.eql(16) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][4].s.r).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][4].s.c).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][4].e.r).be.eql(3) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][4].e.c).be.eql(0) | ||
| }) | ||
| it('should work when using special rowspan layout #9 (using rowspan in different rows)', async () => { | ||
| const stream = await conversion(` | ||
| <table> | ||
| <tr> | ||
| <td rowspan='3'>Row 1 Col 1</td> | ||
| <td>Row 1 Col 2</td> | ||
| <td>Row 1 Col 3</td> | ||
| <td>Row 1 Col 4</td> | ||
| </tr> | ||
| <tr> | ||
| <td rowspan='2'>Row 2 Col 1</td> | ||
| <td rowspan='2'>Row 2 Col 2</td> | ||
| <td>Row 2 Col 3</td> | ||
| </tr> | ||
| <tr> | ||
| <td>Row 3 Col 3</td> | ||
| </tr> | ||
| </table> | ||
| `) | ||
| const parsedXlsx = await new Promise((resolve, reject) => { | ||
| const bufs = [] | ||
| stream.on('error', reject) | ||
| stream.on('data', (d) => { bufs.push(d) }) | ||
| stream.on('end', () => { | ||
| const buf = Buffer.concat(bufs) | ||
| resolve(xlsx.read(buf)) | ||
| }) | ||
| }) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A1'].v).be.eql('Row 1 Col 1') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A2']).be.undefined() | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A3']).be.undefined() | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['B1'].v).be.eql('Row 1 Col 2') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['B2'].v).be.eql('Row 2 Col 1') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['B3']).be.undefined() | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['C1'].v).be.eql('Row 1 Col 3') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['C2'].v).be.eql('Row 2 Col 2') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['C3']).be.undefined() | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['D1'].v).be.eql('Row 1 Col 4') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['D2'].v).be.eql('Row 2 Col 3') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['D3'].v).be.eql('Row 3 Col 3') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.r).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].s.c).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.r).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][0].e.c).be.eql(0) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].s.r).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].s.c).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].e.r).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].e.c).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].s.r).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].s.c).be.eql(1) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].e.r).be.eql(2) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['!merges'][1].e.c).be.eql(1) | ||
| }) | ||
| it('should be able to set fontFamily', async () => { | ||
| const stream = await conversion(` | ||
| <style> | ||
| * { | ||
| font-family: Verdana | ||
| } | ||
| </style> | ||
| <table> | ||
| <tr> | ||
| <td style="font-size: 34px">Hello</td> | ||
| </tr> | ||
| </table> | ||
| `) | ||
| const parsedXlsx = await new Promise((resolve, reject) => { | ||
| const bufs = [] | ||
| stream.on('error', reject) | ||
| stream.on('data', (d) => { bufs.push(d) }) | ||
| stream.on('end', () => { | ||
| const buf = Buffer.concat(bufs) | ||
| resolve(xlsx.read(buf)) | ||
| }) | ||
| }) | ||
| should(parsedXlsx.Styles.Fonts).matchAny((font) => should(font.name).be.eql('Verdana')) | ||
| }) | ||
| it('should wait for JS trigger', async () => { | ||
| const stream = await conversion(` | ||
| <table id="main"> | ||
| </table> | ||
| <script> | ||
| setTimeout(function () { | ||
| var table = document.getElementById('main') | ||
| var row = document.createElement('tr') | ||
| var cell = document.createElement('td') | ||
| cell.innerHTML = 'Hello' | ||
| row.appendChild(cell) | ||
| table.appendChild(row) | ||
| window.CHROME_PAGE_EVAL_READY = true | ||
| window.PHANTOM_PAGE_EVAL_READY = true | ||
| }, 500) | ||
| </script> | ||
| `, { | ||
| waitForJS: true | ||
| }) | ||
| const parsedXlsx = await new Promise((resolve, reject) => { | ||
| const bufs = [] | ||
| stream.on('error', reject) | ||
| stream.on('data', (d) => { bufs.push(d) }) | ||
| stream.on('end', () => { | ||
| const buf = Buffer.concat(bufs) | ||
| resolve(xlsx.read(buf)) | ||
| }) | ||
| }) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A1'].v).be.eql('Hello') | ||
| }) | ||
| it('should wait for JS trigger (custom var name)', async () => { | ||
| const stream = await conversion(` | ||
| <table id="main"> | ||
| </table> | ||
| <script> | ||
| setTimeout(function () { | ||
| var table = document.getElementById('main') | ||
| var row = document.createElement('tr') | ||
| var cell = document.createElement('td') | ||
| cell.innerHTML = 'Hello' | ||
| row.appendChild(cell) | ||
| table.appendChild(row) | ||
| window.READY_TO_START = true | ||
| }, 500) | ||
| </script> | ||
| `, { | ||
| waitForJS: true, | ||
| waitForJSVarName: 'READY_TO_START' | ||
| }) | ||
| const parsedXlsx = await new Promise((resolve, reject) => { | ||
| const bufs = [] | ||
| stream.on('error', reject) | ||
| stream.on('data', (d) => { bufs.push(d) }) | ||
| stream.on('end', () => { | ||
| const buf = Buffer.concat(bufs) | ||
| resolve(xlsx.read(buf)) | ||
| }) | ||
| }) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A1'].v).be.eql('Hello') | ||
| }) | ||
| it('should generate multiple sheets when there are multiple tables in html', async () => { | ||
| const stream = await conversion(` | ||
| <table name="Data1"> | ||
| <tr> | ||
| <td>1</td> | ||
| <td>2</td> | ||
| <td>3</td> | ||
| <td>4</td> | ||
| </tr> | ||
| </table> | ||
| <table name="Data2"> | ||
| <tr> | ||
| <td>1</td> | ||
| <td>2</td> | ||
| <td>3</td> | ||
| <td>4</td> | ||
| </tr> | ||
| </table> | ||
| `) | ||
| const parsedXlsx = await new Promise((resolve, reject) => { | ||
| const bufs = [] | ||
| stream.on('error', reject) | ||
| stream.on('data', (d) => { bufs.push(d) }) | ||
| stream.on('end', () => { | ||
| const buf = Buffer.concat(bufs) | ||
| resolve(xlsx.read(buf)) | ||
| }) | ||
| }) | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['A1'].v).be.eql('1') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['B1'].v).be.eql('2') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['C1'].v).be.eql('3') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[0]]['D1'].v).be.eql('4') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[1]]['A1'].v).be.eql('1') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[1]]['B1'].v).be.eql('2') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[1]]['C1'].v).be.eql('3') | ||
| should(parsedXlsx.Sheets[parsedXlsx.SheetNames[1]]['D1'].v).be.eql('4') | ||
| }) | ||
| it('should callback error when input contains invalid characters', async () => { | ||
| return ( | ||
| conversion('<table><tr><td> </td></tr></table>') | ||
| conversion(` | ||
| <table> | ||
| <tr> | ||
| <td> </td> | ||
| </tr> | ||
| </table> | ||
| `) | ||
| ).should.be.rejected() | ||
@@ -705,10 +1365,24 @@ }) | ||
| it('should translate ampersands', async () => { | ||
| const stream = await conversion('<table><tr><td>& &</td></tr>') | ||
| const stream = await conversion(` | ||
| <table> | ||
| <tr> | ||
| <td>& &</td> | ||
| </tr> | ||
| </table> | ||
| `) | ||
| const bufs = [] | ||
| stream.on('data', (d) => { bufs.push(d) }) | ||
| stream.on('end', () => { | ||
| const buf = Buffer.concat(bufs) | ||
| xlsx.read(buf).Strings[0].t.should.be.eql('& &') | ||
| await new Promise((resolve, reject) => { | ||
| stream.on('data', (d) => { bufs.push(d) }) | ||
| stream.on('error', reject) | ||
| stream.on('end', () => { | ||
| try { | ||
| const buf = Buffer.concat(bufs) | ||
| xlsx.read(buf).Strings[0].t.should.be.eql('& &') | ||
| resolve() | ||
| } catch (e) { | ||
| reject(e) | ||
| } | ||
| }) | ||
| }) | ||
@@ -724,1 +1398,35 @@ }) | ||
| }) | ||
| async function createHtmlFile (html) { | ||
| const outputPath = path.join(tmpDir, `${uuid()}.html`) | ||
| await writeFileAsync(outputPath, html) | ||
| return outputPath | ||
| } | ||
| function rmDir (dirPath) { | ||
| if (!fs.existsSync(dirPath)) { | ||
| fs.mkdirSync(dirPath) | ||
| } | ||
| let files | ||
| try { | ||
| files = fs.readdirSync(dirPath) | ||
| } catch (e) { | ||
| return | ||
| } | ||
| if (files.length > 0) { | ||
| for (let i = 0; i < files.length; i++) { | ||
| let filePath = `${dirPath}/${files[i]}` | ||
| try { | ||
| if (fs.statSync(filePath).isFile()) { | ||
| fs.unlinkSync(filePath) | ||
| } | ||
| } catch (e) { } | ||
| } | ||
| } | ||
| } |
New alerts
Major refactor
Supply chain riskPackage has recently undergone a major refactor. It may be unstable or indicate significant internal changes. Use caution when updating to versions that include significant changes.
Found 1 instance in 1 package
Improved metrics
- Total package byte prevSize
76041
71.38%- Number of package files
14
27.27%- Lines of code
1721
81.35%Worsened metrics
- Dependency count
4
100%- Number of low supply chain risk alerts
3
50%- Number of medium supply chain risk alerts
1
Infinity%Dependency changes
+ Added
moment@2.22.1+ Added
tinycolor2@1.4.1+ Added
xlsx-populate@1.18.0+ Added
adler-32@1.3.1(transitive)+ Added
cfb@1.2.2(transitive)+ Added
crc-32@1.2.2(transitive)+ Added
immediate@3.0.6(transitive)+ Added
jszip@3.10.1(transitive)+ Added
lie@3.3.0(transitive)+ Added
moment@2.22.1(transitive)+ Added
pako@1.0.11(transitive)+ Added
sax@1.4.1(transitive)+ Added
setimmediate@1.0.5(transitive)+ Added
tinycolor2@1.4.1(transitive)+ Added
xlsx-populate@1.18.0(transitive)- Removed
msexcel-builder-extended@0.0.8- Removed
archiver@2.1.1(transitive)- Removed
archiver-utils@1.3.0(transitive)- Removed
async@2.1.2(transitive)- Removed
balanced-match@1.0.2(transitive)- Removed
base64-js@1.5.1(transitive)- Removed
bl@1.2.3(transitive)- Removed
brace-expansion@1.1.11(transitive)- Removed
buffer@5.7.1(transitive)- Removed
buffer-alloc@1.2.0(transitive)- Removed
buffer-alloc-unsafe@1.1.0(transitive)- Removed
buffer-crc32@0.2.13(transitive)- Removed
buffer-fill@1.0.0(transitive)- Removed
compress-commons@1.2.2(transitive)- Removed
concat-map@0.0.1(transitive)- Removed
crc@3.8.0(transitive)- Removed
crc32-stream@2.0.0(transitive)- Removed
end-of-stream@1.4.4(transitive)- Removed
fs-constants@1.0.0(transitive)- Removed
fs-extra@1.0.0(transitive)- Removed
fs.realpath@1.0.0(transitive)- Removed
glob@7.2.3(transitive)- Removed
graceful-fs@4.2.11(transitive)- Removed
ieee754@1.2.1(transitive)- Removed
inflight@1.0.6(transitive)- Removed
jsonfile@2.4.0(transitive)- Removed
klaw@1.3.1(transitive)- Removed
lazystream@1.0.1(transitive)- Removed
minimatch@3.1.2(transitive)- Removed
msexcel-builder-extended@0.0.8(transitive)- Removed
normalize-path@2.1.1(transitive)- Removed
once@1.4.0(transitive)- Removed
path-is-absolute@1.0.1(transitive)- Removed
remove-trailing-separator@1.1.0(transitive)- Removed
tar-stream@1.6.2(transitive)- Removed
to-buffer@1.1.1(transitive)- Removed
wrappy@1.0.2(transitive)- Removed
xmlbuilder@8.2.2(transitive)- Removed
xtend@4.0.2(transitive)- Removed
zip-stream@1.2.0(transitive)