Get list of tags used in document?

[mnpenner]

Environment

• Version of docxtemplater : 3.0.0
• Used docxtemplater-modules : No
• Runner : Browser/Node.JS/... Node v6.9.1

How to reproduce my problem :

Is it possible to get a list of tags used inside a document?

I want to extract all the tags so that I can ask the user some questions before I generate the doc.

[edi9999]

2022 Update

The easiest way is to follow this documentation example : https://docxtemplater.com/docs/faq/#get-list-of-placeholders

Old answer

This is something that can be done using a module. Here is an example :

const _ = require("lodash");

class InspectModule {
    constructor() {
        this.inspect = {};
    }
    set(obj) {
        if (obj.inspect) {
            this.inspect = _.merge({}, this.inspect, obj.inspect);
        }
    }
}

const getTags = function (postParsed) {
    return postParsed.filter(function (part) {
        return part.type === "placeholder";
    }).reduce(function (tags, part) {
        tags[part.value] = {};
        if (part.subparsed) {
            tags[part.value] = getTags(part.subparsed);
        }
        return tags;
    }, {});
}
const doc = new Docxtemplater();
doc.loadZip(...)
const inspectModule = new InspectModule();
doc.attachModule(inspectModule);
try {
    doc.compile()
}
catch (error) {
    var e = {
        message: error.message,
        name: error.name,
        stack: error.stack,
        properties: error.properties,
    }
    console.log(JSON.stringify({error: e}));
    // The error thrown here contains additional information when logged with JSON.stringify (it contains a property object).
    throw error;
}
const postParsed = inspectModule.inspect.postparsed;
console.log(JSON.stringify({p: postParsed}));
console.log(JSON.stringify({tag: getTags(postParsed)}));

However, this is quite experimental, and could potentially break in future releases.

[PaulMcGuinness]

I went for a simpler approach as I was only interested in {#groups}

var a=String(doc.getFullText()).match(/{#[a-z]{1,10}}/g);

but this would return an array of all tags (up to 20 chars in length):-

var a=String(doc.getFullText()).match(/{[a-z]{1,20}}/g);

[bunnyvishal6]

@edi9999 what is testUtils ? in your example code stated above?

const doc = testUtils.createDoc("tag-loop-example.docx");

[edi9999]

It is just a method that creates the doc instead of doing

const doc = new Docxtemplater();
doc.loadZip(...)

[bunnyvishal6]

@edi9999 can you please provide some working code to get tags.

[bunnyvishal6]

@edi9999 here is my code

const _ = require("lodash"),
    path = require('path'),
    JSZip = require('jszip'),
    Docxtemplater = require('docxtemplater'),
    fs = require('fs');

class InspectModule {
    constructor() {
        this.inspect = {};
    }
    set(obj) {
        if (obj.inspect) {
            this.inspect = _.merge({}, this.inspect, obj.inspect);
        }
    }
}

const getTags = function (postParsed) {
    return postParsed.filter(function (part) {
        return part.type === "placeholder";
    }).reduce(function (tags, part) {
        tags[part.value] = {};
        if (part.subparsed) {
            tags[part.value] = getTags(part.subparsed);
        }
        return tags;
    }, {});
}

//Load the docx file as a binary
let content = fs
.readFileSync(path.resolve(__dirname, 'docs/test.docx'), 'binary');
let zip = new JSZip(content);
let doc = new Docxtemplater();
doc.loadZip(zip);
let inspectModule = new InspectModule();
doc.attachModule(inspectModule);
doc.render();
let postParsed = inspectModule.inspect.postparsed;
console.log(JSON.stringify({p: postParsed}));
console.log(JSON.stringify({tag: getTags(postParsed)}));
[template.zip](https://github.com/open-xml-templating/docxtemplater/files/1435172/template.zip)

here is the error I get

G:\learn\test\node_modules\docxtemplater\js\errors.js:52
        throw err;
        ^
Error: Multi error
    at new XTTemplateError (G:\learn\test\node_modules\docxtemplater\js\errors.js:19:15)
    at throwMultiError (G:\learn\test\node_modules\docxtemplater\js\errors.js:46:12)
    at XmlTemplater.errorChecker (G:\learn\test\node_modules\docxtemplater\js\xml-templater.js:119:5)
    at XmlTemplater.parse (G:\learn\test\node_modules\docxtemplater\js\xml-templater.js:104:9)
    at Docxtemplater.compileFile (G:\learn\test\node_modules\docxtemplater\js\docxtemplater.js:88:16)
    at G:\learn\test\node_modules\docxtemplater\js\docxtemplater.js:119:13
    at Array.forEach (<anonymous>)
    at Docxtemplater.compile (G:\learn\test\node_modules\docxtemplater\js\docxtemplater.js:117:24)
    at Docxtemplater.render (G:\learn\test\node_modules\docxtemplater\js\docxtemplater.js:160:9)

[edi9999]

Ok, I see, this happens becaus of a rendering error probably.

Can you try to replace doc.render() by doc.compile() and see if that helps ?

[edi9999]

I have also updated the code above with a try / catch statement. Can you update your code and report the result ?

[bunnyvishal6]

@edi9999 sorry for late reply. I got error even after changing doc.render() to doc.compile().
here is my code

const _ = require("lodash"),
    path = require('path'),
    JSZip = require('jszip'),
    Docxtemplater = require('docxtemplater'),
    fs = require('fs');

class InspectModule {
    constructor() {
        this.inspect = {};
    }
    set(obj) {
        if (obj.inspect) {
            this.inspect = _.merge({}, this.inspect, obj.inspect);
        }
    }
}

const getTags = function (postParsed) {
    return postParsed.filter(function (part) {
        return part.type === "placeholder";
    }).reduce(function (tags, part) {
        tags[part.value] = {};
        if (part.subparsed) {
            tags[part.value] = getTags(part.subparsed);
        }
        return tags;
    }, {});
}

//Load the docx file as a binary
let content = fs
.readFileSync(path.resolve(__dirname, 'docs/test.docx'), 'binary');
let zip = new JSZip(content);
let doc = new Docxtemplater();
doc.loadZip(zip);
let inspectModule = new InspectModule();
doc.attachModule(inspectModule);
try {
    doc.compile()
}
catch (error) {
    var e = {
        message: error.message,
        name: error.name,
        stack: error.stack,
        properties: error.properties,
    }
    console.log(JSON.stringify({error: e}));
    // The error thrown here contains additional information when logged with JSON.stringify (it contains a property object).
    throw error;
}
let postParsed = inspectModule.inspect.postparsed;
console.log(JSON.stringify({p: postParsed}));
console.log(JSON.stringify({tag: getTags(postParsed)}));

here is the error I get

PS G:\learn\test> node server.js
{}
G:\learn\test\server.js:19
    return postParsed.filter(function (part) {
                      ^

TypeError: Cannot read property 'filter' of undefined
    at getTags (G:\learn\test\server.js:19:23)
    at Object.<anonymous> (G:\learn\test\server.js:54:34)
    at Module._compile (module.js:635:30)
    at Object.Module._extensions..js (module.js:646:10)
    at Module.load (module.js:554:32)
    at tryModuleLoad (module.js:497:12)
    at Function.Module._load (module.js:489:3)
    at Function.Module.runMain (module.js:676:10)
    at startup (bootstrap_node.js:187:16)
    at bootstrap_node.js:608:3
[test.zip](https://github.com/open-xml-templating/docxtemplater/files/1436789/test.zip)

[edi9999]

Can you do

console.log(JSON.stringify({"iModule": iModule}));

just after doc.compile()

Are you running version 3.1.11 of docxtemplater ?

[bunnyvishal6]

@edi9999 yes I'm using docxtemplater version 3.1.11
here I added console.log(JSON.stringify({"iModule": inspectModule})); after doc.compile()

const _ = require("lodash"),
    path = require('path'),
    JSZip = require('jszip'),
    Docxtemplater = require('docxtemplater'),
    fs = require('fs');

class InspectModule {
    constructor() {
        this.inspect = {};
    }
    set(obj) {
        if (obj.inspect) {
            this.inspect = _.merge({}, this.inspect, obj.inspect);
        }
    }
}

const getTags = function (postParsed) {
    return postParsed.filter(function (part) {
        return part.type === "placeholder";
    }).reduce(function (tags, part) {
        tags[part.value] = {};
        if (part.subparsed) {
            tags[part.value] = getTags(part.subparsed);
        }
        return tags;
    }, {});
}

//Load the docx file as a binary
let content = fs
.readFileSync(path.resolve(__dirname, 'docs/test.docx'), 'binary');
let zip = new JSZip(content);
let doc = new Docxtemplater();
doc.loadZip(zip);
let inspectModule = new InspectModule();
doc.attachModule(inspectModule);
try {
    doc.compile();
    console.log(JSON.stringify({"iModule": inspectModule}));
}
catch (error) {
    var e = {
        message: error.message,
        name: error.name,
        stack: error.stack,
        properties: error.properties,
    }
    console.log(JSON.stringify({error: e}));
    // The error thrown here contains additional information when logged with JSON.stringify (it contains a property object).
    throw error;
}
let postParsed = inspectModule.inspect.postparsed;
console.log(JSON.stringify({p: postParsed}));
console.log(JSON.stringify({tag: getTags(postParsed)}));

here is the url to gist file containing the output
https://gist.github.com/bunnyvishal6/d3d0210de25d3a05bdcab01ec3adcf13

[edi9999]

Can you update to docxtemplater 3.1.12. It should work with that version

[edi9999]

(I just published it)

[bunnyvishal6]

@edi9999 Awesome! thank you very much. please consider including getTag method to docxtemplater.

[edi9999]

It is now possible to get the list of tags of the document by writing less code.

https://docxtemplater.readthedocs.io/en/latest/faq.html#get-list-of-placeholders

[bunnyvishal6]

@edi9999 awesome thank you.