Huge News!Announcing our $40M Series B led by Abstract Ventures.Learn More →
pdfreader - npm Package Compare versions
Comparing version 1.3.1 to 1.4.0
@@ -68,2 +68,3 @@ /** | ||
| /** @returns an 3-dimension matrix: row -> column -> items_collisionning_in_column -> item */ | ||
| TableParser.prototype.getMatrix = function () { | ||
@@ -83,2 +84,15 @@ var rows = this.getRows(); | ||
| /** | ||
| * For use with console.table(). | ||
| * @param {String} collisionSeparator separator to use when there are multiple values to join for a given column | ||
| * @returns a 2-dimension matrix: row -> column -> value | ||
| */ | ||
| TableParser.prototype.getCleanMatrix = function ({ collisionSeparator } = {}) { | ||
| return this.getMatrix().map((rowColumns) => | ||
| rowColumns.map((items) => | ||
| items.map((item) => item.text).join(collisionSeparator || "") | ||
| ) | ||
| ); | ||
| }; | ||
| function getText(item) { | ||
@@ -85,0 +99,0 @@ return item.text; |
| { | ||
| "name": "pdfreader", | ||
| "version": "1.3.1", | ||
| "version": "1.4.0", | ||
| "description": "Read text and parse tables from PDF files. Supports tabular data with automatic column detection, and rule-based parsing.", | ||
@@ -5,0 +5,0 @@ "main": "index.js", |
161
README.md
@@ -1,2 +0,2 @@ | ||
| # pdfreader  [](https://www.codacy.com/app/adrien-joly/npm-pdfreader?utm_source=github.com&utm_medium=referral&utm_content=adrienjoly/npm-pdfreader&utm_campaign=Badge_Grade) | ||
| # pdfreader  [](https://app.codacy.com/gh/adrienjoly/npm-pdfreader?utm_source=github.com&utm_medium=referral&utm_content=adrienjoly/npm-pdfreader&utm_campaign=Badge_Grade) | ||
@@ -57,4 +57,17 @@ Read text and parse tables from PDF files. | ||
| ### Raw PDF reading from a PDF already in memory (buffer) | ||
| ### Parsing a password-protected PDF file | ||
| ```javascript | ||
| new PdfReader({ password: "YOUR_PASSWORD" }).parseFileItems( | ||
| "test/sample-with-password.pdf", | ||
| function (err, item) { | ||
| if (err) console.error(err); | ||
| else if (!item) console.warn("end of file"); | ||
| else if (item.text) console.log(item.text); | ||
| } | ||
| ); | ||
| ``` | ||
| ### Raw PDF reading from a PDF buffer | ||
| As above, but reading from a buffer in memory rather than from a file referenced by path. For example: | ||
@@ -76,151 +89,17 @@ | ||
| ### Example: reading from a buffer of an online PDF | ||
| ### Other examples of use | ||
| ```javascript | ||
| const get = (url) => | ||
| new Promise((resolve, reject) => | ||
| https | ||
| .get(url, (res) => { | ||
| const data = []; | ||
| res | ||
| .on("data", (chunk) => data.push(chunk)) | ||
| .on("end", () => resolve(Buffer.concat(data))); | ||
| }) | ||
| .on("error", reject) | ||
| ); | ||
| function addTextToLines(textLines, item) { | ||
| const existingLine = textLines.find(({ y }) => y === item.y); | ||
| if (existingLine) { | ||
| existingLine.text += " " + item.text; | ||
| } else { | ||
| textLines.push(item); | ||
| } | ||
| } | ||
| const parseLinesPerPage = (buffer) => | ||
| new Promise((resolve, reject) => { | ||
| const linesPerPage = []; | ||
| let pageNumber = 0; | ||
| new PdfReader().parseBuffer(buffer, (err, item) => { | ||
| if (err) reject(err); | ||
| else if (!item) { | ||
| resolve(linesPerPage.map((page) => page.map((line) => line.text))); | ||
| } else if (item.page) { | ||
| pageNumber = item.page - 1; | ||
| linesPerPage[pageNumber] = []; | ||
| } else if (item.text) { | ||
| addTextToLines(linesPerPage[pageNumber], item); | ||
| } | ||
| }); | ||
| }); | ||
| const url = new URL( | ||
| "https://raw.githubusercontent.com/adrienjoly/npm-pdfreader/master/test/sample.pdf" | ||
| ); | ||
| const buffer = get(url) | ||
| .then((buffer) => parseLinesPerPage(buffer)) | ||
| .then((linesPerPage) => console.log(linesPerPage)); | ||
| ``` | ||
| ### Example: parsing lines of text from a PDF file | ||
|  | ||
| Here is the code required to convert this PDF file into text: | ||
| ```js | ||
| const { PdfReader } = require("pdfreader"); | ||
| let rows = {}; // indexed by y-position | ||
| function flushRows() { | ||
| Object.keys(rows) // => array of y-positions (type: float) | ||
| .sort((y1, y2) => parseFloat(y1) - parseFloat(y2)) // sort float positions | ||
| .forEach((y) => console.log((rows[y] || []).join(""))); | ||
| rows = {}; // clear rows for next page | ||
| } | ||
| new PdfReader().parseFileItems("test/sample.pdf", (err, item) => { | ||
| if (err) { | ||
| console.error({ err }); | ||
| } else if (!item) { | ||
| flushRows(); | ||
| console.log("END OF FILE"); | ||
| } else if (item.page) { | ||
| flushRows(); // print the rows of the previous page | ||
| console.log("PAGE:", item.page); | ||
| } else if (item.text) { | ||
| // accumulate text items into rows object, per line | ||
| (rows[item.y] = rows[item.y] || []).push(item.text); | ||
| } | ||
| }); | ||
| ``` | ||
| Fork this example from [parsing a CV/résumé](https://github.com/adrienjoly/npm-pdfreader-example). | ||
| ### Example: parsing a table from a PDF file | ||
|  | ||
| Here is the code required to convert this PDF file into a textual table: | ||
| Source code of the examples above: [parsing a CV/résumé](https://github.com/adrienjoly/npm-pdfreader-example). | ||
| ```js | ||
| var pdfreader = require("pdfreader"); | ||
| For more, see [Examples of use](https://github.com/adrienjoly/npm-pdfreader/discussions/categories/examples-of-use). | ||
| const nbCols = 2; | ||
| const cellPadding = 40; // each cell is padded to fit 40 characters | ||
| const columnQuantitizer = (item) => parseFloat(item.x) >= 20; | ||
| const padColumns = (array, nb) => | ||
| Array.apply(null, { length: nb }).map((val, i) => array[i] || []); | ||
| // .. because map() skips undefined elements | ||
| const mergeCells = (cells) => | ||
| (cells || []) | ||
| .map((cell) => cell.text) | ||
| .join("") // merge cells | ||
| .substr(0, cellPadding) | ||
| .padEnd(cellPadding, " "); // padding | ||
| const renderMatrix = (matrix) => | ||
| (matrix || []) | ||
| .map((row, y) => padColumns(row, nbCols).map(mergeCells).join(" | ")) | ||
| .join("\n"); | ||
| var table = new pdfreader.TableParser(); | ||
| new pdfreader.PdfReader().parseFileItems(filename, function (err, item) { | ||
| if (!item || item.page) { | ||
| // end of file, or page | ||
| console.log(renderMatrix(table.getMatrix())); | ||
| console.log("PAGE:", item.page); | ||
| table = new pdfreader.TableParser(); // new/clear table for next page | ||
| } else if (item.text) { | ||
| // accumulate text items into rows object, per line | ||
| table.processItem(item, columnQuantitizer(item)); | ||
| } | ||
| }); | ||
| ``` | ||
| Fork this example from [parsing a CV/résumé](https://github.com/adrienjoly/npm-pdfreader-example). | ||
| ## Example: opening a PDF file with a password | ||
| ```javascript | ||
| new PdfReader({ password: "YOUR_PASSWORD" }).parseFileItems( | ||
| "test/sample-with-password.pdf", | ||
| function (err, item) { | ||
| if (err) console.error(err); | ||
| else if (!item) console.warn("end of file"); | ||
| else if (item.text) console.log(item.text); | ||
| } | ||
| ); | ||
| ``` | ||
| ## Rule-based data extraction | ||
| The Rule class can be used to define and process data extraction rules, while parsing a PDF document. | ||
| The `Rule` class can be used to define and process data extraction rules, while parsing a PDF document. | ||
| Rule instances expose "accumulators": methods that defines the data extraction strategy to be used for each rule. | ||
| `Rule` instances expose "accumulators": methods that defines the data extraction strategy to be used for each rule. | ||
@@ -227,0 +106,0 @@ Example: |
New alerts
License Policy Violation
LicenseThis package is not allowed per your license policy. Review the package's license to ensure compliance.
Found 1 instance in 1 package
Fixed alerts
License Policy Violation
LicenseThis package is not allowed per your license policy. Review the package's license to ensure compliance.
Found 1 instance in 1 package
Improved metrics
- Lines of code
- increased by1.86%
713
Worsened metrics
- Total package byte prevSize
- decreased by-7.73%
35130
- Number of lines in readme file
- decreased by-45.32%
146
No dependency changes