From 48056ea1bd731e3023fdb840d1867b5128fe5da3 Mon Sep 17 00:00:00 2001 From: rafaelsideguide <150964962+rafaelsideguide@users.noreply.github.com> Date: Mon, 2 Sep 2024 14:15:56 -0300 Subject: [PATCH 1/5] feat: added go html to md parser --- .../lib/__tests__/html-to-markdown.test.ts | 29 ++++ apps/api/src/lib/go-html-to-md/go.mod | 11 ++ apps/api/src/lib/go-html-to-md/go.sum | 81 +++++++++ .../src/lib/go-html-to-md/html-to-markdown.go | 41 +++++ apps/api/src/lib/html-to-markdown.ts | 162 +++++++++++------- 5 files changed, 260 insertions(+), 64 deletions(-) create mode 100644 apps/api/src/lib/__tests__/html-to-markdown.test.ts create mode 100644 apps/api/src/lib/go-html-to-md/go.mod create mode 100644 apps/api/src/lib/go-html-to-md/go.sum create mode 100644 apps/api/src/lib/go-html-to-md/html-to-markdown.go diff --git a/apps/api/src/lib/__tests__/html-to-markdown.test.ts b/apps/api/src/lib/__tests__/html-to-markdown.test.ts new file mode 100644 index 00000000..00db7758 --- /dev/null +++ b/apps/api/src/lib/__tests__/html-to-markdown.test.ts @@ -0,0 +1,29 @@ +import { parseMarkdown } from '../html-to-markdown'; + +describe('parseMarkdown', () => { + it('should correctly convert simple HTML to Markdown', async () => { + const html = '

Hello, world!

'; + const expectedMarkdown = 'Hello, world!'; + await expect(parseMarkdown(html)).resolves.toBe(expectedMarkdown); + }); + + it('should convert complex HTML with nested elements to Markdown', async () => { + const html = '

Hello bold world!

'; + const expectedMarkdown = 'Hello **bold** world!\n\n- List item'; + await expect(parseMarkdown(html)).resolves.toBe(expectedMarkdown); + }); + + it('should return empty string when input is empty', async () => { + const html = ''; + const expectedMarkdown = ''; + await expect(parseMarkdown(html)).resolves.toBe(expectedMarkdown); + }); + + it('should handle null input gracefully', async () => { + const html = null; + const expectedMarkdown = ''; + await expect(parseMarkdown(html)).resolves.toBe(expectedMarkdown); + }); + + +}); diff --git a/apps/api/src/lib/go-html-to-md/go.mod b/apps/api/src/lib/go-html-to-md/go.mod new file mode 100644 index 00000000..40cce17d --- /dev/null +++ b/apps/api/src/lib/go-html-to-md/go.mod @@ -0,0 +1,11 @@ +module html-to-markdown.go + +go 1.22.6 + +require github.com/JohannesKaufmann/html-to-markdown v1.6.0 + +require ( + github.com/PuerkitoBio/goquery v1.9.2 // indirect + github.com/andybalholm/cascadia v1.3.2 // indirect + golang.org/x/net v0.25.0 // indirect +) diff --git a/apps/api/src/lib/go-html-to-md/go.sum b/apps/api/src/lib/go-html-to-md/go.sum new file mode 100644 index 00000000..59bcf2f9 --- /dev/null +++ b/apps/api/src/lib/go-html-to-md/go.sum @@ -0,0 +1,81 @@ +github.com/JohannesKaufmann/html-to-markdown v1.6.0 h1:04VXMiE50YYfCfLboJCLcgqF5x+rHJnb1ssNmqpLH/k= +github.com/JohannesKaufmann/html-to-markdown v1.6.0/go.mod h1:NUI78lGg/a7vpEJTz/0uOcYMaibytE4BUOQS8k78yPQ= +github.com/PuerkitoBio/goquery v1.9.2 h1:4/wZksC3KgkQw7SQgkKotmKljk0M6V8TUvA8Wb4yPeE= +github.com/PuerkitoBio/goquery v1.9.2/go.mod h1:GHPCaP0ODyyxqcNoFGYlAprUFH81NuRPd0GX3Zu2Mvk= +github.com/andybalholm/cascadia v1.3.2 h1:3Xi6Dw5lHF15JtdcmAHD3i1+T8plmv7BQ/nsViSLyss= +github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU= +github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo= +github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ= +github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI= +github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0= +github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= +github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= +github.com/sebdah/goldie/v2 v2.5.3 h1:9ES/mNN+HNUbNWpVAlrzuZ7jE+Nrczbj8uFRjM7624Y= +github.com/sebdah/goldie/v2 v2.5.3/go.mod h1:oZ9fp0+se1eapSRjfYbsV/0Hqhbuu3bJVvKI/NNtssI= +github.com/sergi/go-diff v1.0.0/go.mod h1:0CfEIISq7TuYL3j771MWULgwwjU+GofnZX9QAmXWZgo= +github.com/sergi/go-diff v1.3.1 h1:xkr+Oxo4BOQKmkn/B9eMK0g5Kg/983T9DqqPHwYqD+8= +github.com/sergi/go-diff v1.3.1/go.mod h1:aMJSSKb2lpPvRNec0+w3fl7LP9IOFzdc9Pa4NFbPK1I= +github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= +github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI= +github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4= +github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY= +github.com/yuin/goldmark v1.7.1 h1:3bajkSilaCbjdKVsKdZjZCLBNPL9pYzrCakKaf4U49U= +github.com/yuin/goldmark v1.7.1/go.mod h1:uzxRWxtg69N339t3louHJ7+O03ezfj6PlliRlaOzY1E= +golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w= +golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc= +golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU= +golang.org/x/crypto v0.22.0/go.mod h1:vr6Su+7cTlO45qkww3VDJlzDn0ctJvRgYbC2NvXHt+M= +golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8= +golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4= +golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs= +golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s= +golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg= +golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c= +golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs= +golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns= +golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg= +golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44= +golang.org/x/net v0.24.0/go.mod h1:2Q7sJY5mzlzWjKtYUEXSlBWCdyaioyXzRB2RtU8KVE8= +golang.org/x/net v0.25.0 h1:d/OCCoBEUq33pjydKrGQhw7IlUPI2Oylr+8qLx49kac= +golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM= +golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= +golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.7.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= +golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= +golang.org/x/sys v0.19.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= +golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= +golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= +golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8= +golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k= +golang.org/x/term v0.7.0/go.mod h1:P32HKFT3hSsZrRxla30E9HqToFYAQPCMs/zFMBUFqPY= +golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo= +golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk= +golang.org/x/term v0.19.0/go.mod h1:2CuTdWZ7KHSQwUzKva0cbMg6q2DMI3Mmxp+gKJbskEk= +golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY= +golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= +golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ= +golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ= +golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8= +golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8= +golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU= +golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU= +golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= +golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= +golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc= +golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU= +golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= +gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI= +gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY= +gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ= diff --git a/apps/api/src/lib/go-html-to-md/html-to-markdown.go b/apps/api/src/lib/go-html-to-md/html-to-markdown.go new file mode 100644 index 00000000..474c8324 --- /dev/null +++ b/apps/api/src/lib/go-html-to-md/html-to-markdown.go @@ -0,0 +1,41 @@ +package main + +import ( + "flag" + "fmt" + "log" + "sync" + + md "github.com/JohannesKaufmann/html-to-markdown" + "github.com/JohannesKaufmann/html-to-markdown/plugin" +) + +func convertHTMLToMarkdown(html string, wg *sync.WaitGroup, results chan<- string) { + defer wg.Done() + converter := md.NewConverter("", true, nil) + converter.Use(plugin.GitHubFlavored()) + + markdown, err := converter.ConvertString(html) + if err != nil { + log.Fatal(err) + } + results <- markdown +} + +func main() { + html := flag.String("html", "", "") + flag.Parse() + + var wg sync.WaitGroup + results := make(chan string, 1) + + wg.Add(1) + go convertHTMLToMarkdown(*html, &wg, results) + + wg.Wait() + close(results) + + for markdown := range results { + fmt.Println(markdown) + } +} diff --git a/apps/api/src/lib/html-to-markdown.ts b/apps/api/src/lib/html-to-markdown.ts index 002cb7be..04fec4c6 100644 --- a/apps/api/src/lib/html-to-markdown.ts +++ b/apps/api/src/lib/html-to-markdown.ts @@ -1,74 +1,108 @@ -export async function parseMarkdown(html: string) { - var TurndownService = require("turndown"); - var turndownPluginGfm = require('joplin-turndown-plugin-gfm') +import { spawn } from 'node:child_process'; +import { join } from 'node:path'; +export async function parseMarkdown(html: string): Promise { + if (!html) { + return ''; + } + + if (process.env.USE_GO_MARKDOWN_PARSER == "true") { + const goScriptPath = join(__dirname, 'go-html-to-md/html-to-markdown.go'); + const goModDir = join(__dirname, 'go-html-to-md'); + const child = spawn('go', ['run', goScriptPath, '--html', html], { + cwd: goModDir, + }); + + return new Promise((resolve, reject) => { + let data = ''; + + child.stdout.on('data', (chunk) => { + data += chunk.toString(); // Convert Buffer to string + }); + + child.stderr.on('data', (chunk) => { + reject(chunk.toString()); // Convert Buffer to string before rejecting + }); + + child.on('close', (code) => { + if (code === 0) { + resolve(data.trim()); + } else { + reject(new Error(`Process exited with code ${code}`)); + } + }); + }); + } else { + var TurndownService = require("turndown"); + var turndownPluginGfm = require('joplin-turndown-plugin-gfm') + + const turndownService = new TurndownService(); + turndownService.addRule("inlineLink", { + filter: function (node, options) { + return ( + options.linkStyle === "inlined" && + node.nodeName === "A" && + node.getAttribute("href") + ); + }, + replacement: function (content, node) { + var href = node.getAttribute("href").trim(); + var title = node.title ? ' "' + node.title + '"' : ""; + return "[" + content.trim() + "](" + href + title + ")\n"; + }, + }); + var gfm = turndownPluginGfm.gfm; + turndownService.use(gfm); + let markdownContent = ""; + const turndownPromise = new Promise((resolve, reject) => { + try { + const result = turndownService.turndown(html); + resolve(result); + } catch (error) { + reject("Error converting HTML to Markdown: " + error); + } + }); + + const timeoutPromise = new Promise((resolve, reject) => { + const timeout = 5000; // Timeout in milliseconds + setTimeout(() => reject("Conversion timed out after " + timeout + "ms"), timeout); + }); - const turndownService = new TurndownService(); - turndownService.addRule("inlineLink", { - filter: function (node, options) { - return ( - options.linkStyle === "inlined" && - node.nodeName === "A" && - node.getAttribute("href") - ); - }, - replacement: function (content, node) { - var href = node.getAttribute("href").trim(); - var title = node.title ? ' "' + node.title + '"' : ""; - return "[" + content.trim() + "](" + href + title + ")\n"; - }, - }); - var gfm = turndownPluginGfm.gfm; - turndownService.use(gfm); - let markdownContent = ""; - const turndownPromise = new Promise((resolve, reject) => { try { - const result = turndownService.turndown(html); - resolve(result); + markdownContent = await Promise.race([turndownPromise, timeoutPromise]); } catch (error) { - reject("Error converting HTML to Markdown: " + error); + console.error(error); + return ""; // Optionally return an empty string or handle the error as needed } - }); - const timeoutPromise = new Promise((resolve, reject) => { - const timeout = 5000; // Timeout in milliseconds - setTimeout(() => reject("Conversion timed out after " + timeout + "ms"), timeout); - }); + // multiple line links + let insideLinkContent = false; + let newMarkdownContent = ""; + let linkOpenCount = 0; + for (let i = 0; i < markdownContent.length; i++) { + const char = markdownContent[i]; - try { - markdownContent = await Promise.race([turndownPromise, timeoutPromise]); - } catch (error) { - console.error(error); - return ""; // Optionally return an empty string or handle the error as needed + if (char == "[") { + linkOpenCount++; + } else if (char == "]") { + linkOpenCount = Math.max(0, linkOpenCount - 1); + } + insideLinkContent = linkOpenCount > 0; + + if (insideLinkContent && char == "\n") { + newMarkdownContent += "\\" + "\n"; + } else { + newMarkdownContent += char; + } + } + markdownContent = newMarkdownContent; + + // Remove [Skip to Content](#page) and [Skip to content](#skip) + markdownContent = markdownContent.replace( + /\[Skip to Content\]\(#[^\)]*\)/gi, + "" + ); + return markdownContent; } - - // multiple line links - let insideLinkContent = false; - let newMarkdownContent = ""; - let linkOpenCount = 0; - for (let i = 0; i < markdownContent.length; i++) { - const char = markdownContent[i]; - - if (char == "[") { - linkOpenCount++; - } else if (char == "]") { - linkOpenCount = Math.max(0, linkOpenCount - 1); - } - insideLinkContent = linkOpenCount > 0; - - if (insideLinkContent && char == "\n") { - newMarkdownContent += "\\" + "\n"; - } else { - newMarkdownContent += char; - } - } - markdownContent = newMarkdownContent; - - // Remove [Skip to Content](#page) and [Skip to content](#skip) - markdownContent = markdownContent.replace( - /\[Skip to Content\]\(#[^\)]*\)/gi, - "" - ); - return markdownContent; } From 291d9e375b27e442e5928e6e5a62e1a96e35d674 Mon Sep 17 00:00:00 2001 From: rafaelsideguide <150964962+rafaelsideguide@users.noreply.github.com> Date: Tue, 3 Sep 2024 10:56:07 -0300 Subject: [PATCH 2/5] now using compiled go/C lib with koffi --- apps/api/Dockerfile | 12 +- apps/api/package.json | 1 + apps/api/pnpm-lock.yaml | 8 + apps/api/src/lib/go-html-to-md/README.md | 7 + apps/api/src/lib/go-html-to-md/go.mod | 5 +- apps/api/src/lib/go-html-to-md/go.sum | 12 ++ .../src/lib/go-html-to-md/html-to-markdown.go | 28 +-- apps/api/src/lib/html-to-markdown.ts | 178 +++++++++--------- apps/test-suite/tests/scrape.test.ts | 11 +- 9 files changed, 144 insertions(+), 118 deletions(-) create mode 100644 apps/api/src/lib/go-html-to-md/README.md diff --git a/apps/api/Dockerfile b/apps/api/Dockerfile index 3ffede0d..a4a2c76b 100644 --- a/apps/api/Dockerfile +++ b/apps/api/Dockerfile @@ -17,8 +17,15 @@ RUN pnpm install RUN --mount=type=secret,id=SENTRY_AUTH_TOKEN \ bash -c 'export SENTRY_AUTH_TOKEN="$(cat /run/secrets/SENTRY_AUTH_TOKEN)"; if [ -z $SENTRY_AUTH_TOKEN ]; then pnpm run build:nosentry; else pnpm run build; fi' -# Install packages needed for deployment +# Install Go 1.19 +FROM golang:1.19 AS go-base +COPY src/lib/go-html-to-md /app/src/lib/go-html-to-md +# Install Go dependencies and build +RUN cd /app/src/lib/go-html-to-md && \ + go mod tidy && \ + go build -o html-to-markdown.so -buildmode=c-shared html-to-markdown.go && \ + chmod +x html-to-markdown.so FROM base RUN apt-get update -qq && \ @@ -26,8 +33,7 @@ RUN apt-get update -qq && \ rm -rf /var/lib/apt/lists /var/cache/apt/archives COPY --from=prod-deps /app/node_modules /app/node_modules COPY --from=build /app /app - - +COPY --from=go-base /app/src/lib/go-html-to-md/html-to-markdown.so /app/src/lib/go-html-to-md/html-to-markdown.so # Start the server by default, this can be overwritten at runtime diff --git a/apps/api/package.json b/apps/api/package.json index bac13e79..dc26b34b 100644 --- a/apps/api/package.json +++ b/apps/api/package.json @@ -86,6 +86,7 @@ "joplin-turndown-plugin-gfm": "^1.0.12", "json-schema-to-zod": "^2.3.0", "keyword-extractor": "^0.0.28", + "koffi": "^2.9.0", "langchain": "^0.2.8", "languagedetect": "^2.0.0", "logsnag": "^1.0.0", diff --git a/apps/api/pnpm-lock.yaml b/apps/api/pnpm-lock.yaml index 2762a84c..b8f876a8 100644 --- a/apps/api/pnpm-lock.yaml +++ b/apps/api/pnpm-lock.yaml @@ -122,6 +122,9 @@ importers: keyword-extractor: specifier: ^0.0.28 version: 0.0.28 + koffi: + specifier: ^2.9.0 + version: 2.9.0 langchain: specifier: ^0.2.8 version: 0.2.8(@supabase/supabase-js@2.44.2)(axios@1.7.2)(cheerio@1.0.0-rc.12)(handlebars@4.7.8)(html-to-text@9.0.5)(ioredis@5.4.1)(mammoth@1.7.2)(mongodb@6.6.2(socks@2.8.3))(openai@4.57.0(zod@3.23.8))(pdf-parse@1.1.1)(puppeteer@22.12.1(typescript@5.4.5))(redis@4.6.14)(ws@8.18.0) @@ -3170,6 +3173,9 @@ packages: resolution: {integrity: sha512-eTIzlVOSUR+JxdDFepEYcBMtZ9Qqdef+rnzWdRZuMbOywu5tO2w2N7rqjoANZ5k9vywhL6Br1VRjUIgTQx4E8w==} engines: {node: '>=6'} + koffi@2.9.0: + resolution: {integrity: sha512-KCsuJ2gM58n6bNdR2Z7gqsh/3TchxxQFbVgax2/UvAjRTgwNSYAJDx9E3jrkBP4jEDHWRCfE47Y2OG+/fiSvEw==} + langchain@0.2.8: resolution: {integrity: sha512-kb2IOMA71xH8e6EXFg0l4S+QSMC/c796pj1+7mPBkR91HHwoyHZhFRrBaZv4tV+Td+Ba91J2uEDBmySklZLpNQ==} engines: {node: '>=18'} @@ -8492,6 +8498,8 @@ snapshots: kleur@3.0.3: {} + koffi@2.9.0: {} + langchain@0.2.8(@supabase/supabase-js@2.44.2)(axios@1.7.2)(cheerio@1.0.0-rc.12)(handlebars@4.7.8)(html-to-text@9.0.5)(ioredis@5.4.1)(mammoth@1.7.2)(mongodb@6.6.2(socks@2.8.3))(openai@4.57.0(zod@3.23.8))(pdf-parse@1.1.1)(puppeteer@22.12.1(typescript@5.4.5))(redis@4.6.14)(ws@8.18.0): dependencies: '@langchain/core': 0.2.12(langchain@0.2.8(@supabase/supabase-js@2.44.2)(axios@1.7.2)(cheerio@1.0.0-rc.12)(handlebars@4.7.8)(html-to-text@9.0.5)(ioredis@5.4.1)(mammoth@1.7.2)(mongodb@6.6.2(socks@2.8.3))(openai@4.57.0(zod@3.23.8))(pdf-parse@1.1.1)(puppeteer@22.12.1(typescript@5.4.5))(redis@4.6.14)(ws@8.18.0))(openai@4.57.0(zod@3.23.8)) diff --git a/apps/api/src/lib/go-html-to-md/README.md b/apps/api/src/lib/go-html-to-md/README.md new file mode 100644 index 00000000..4ad510c3 --- /dev/null +++ b/apps/api/src/lib/go-html-to-md/README.md @@ -0,0 +1,7 @@ +To build the go-html-to-md library, run the following command: + +```bash +cd apps/api/src/lib/go-html-to-md +go build -o html-to-markdown.so -buildmode=c-shared html-to-markdown.go +chmod +x html-to-markdown.so +``` \ No newline at end of file diff --git a/apps/api/src/lib/go-html-to-md/go.mod b/apps/api/src/lib/go-html-to-md/go.mod index 40cce17d..0836f441 100644 --- a/apps/api/src/lib/go-html-to-md/go.mod +++ b/apps/api/src/lib/go-html-to-md/go.mod @@ -1,11 +1,14 @@ module html-to-markdown.go -go 1.22.6 +go 1.19 require github.com/JohannesKaufmann/html-to-markdown v1.6.0 require ( github.com/PuerkitoBio/goquery v1.9.2 // indirect github.com/andybalholm/cascadia v1.3.2 // indirect + github.com/kr/pretty v0.3.0 // indirect golang.org/x/net v0.25.0 // indirect + gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c // indirect + gopkg.in/yaml.v2 v2.4.0 // indirect ) diff --git a/apps/api/src/lib/go-html-to-md/go.sum b/apps/api/src/lib/go-html-to-md/go.sum index 59bcf2f9..7961629d 100644 --- a/apps/api/src/lib/go-html-to-md/go.sum +++ b/apps/api/src/lib/go-html-to-md/go.sum @@ -4,14 +4,22 @@ github.com/PuerkitoBio/goquery v1.9.2 h1:4/wZksC3KgkQw7SQgkKotmKljk0M6V8TUvA8Wb4 github.com/PuerkitoBio/goquery v1.9.2/go.mod h1:GHPCaP0ODyyxqcNoFGYlAprUFH81NuRPd0GX3Zu2Mvk= github.com/andybalholm/cascadia v1.3.2 h1:3Xi6Dw5lHF15JtdcmAHD3i1+T8plmv7BQ/nsViSLyss= github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU= +github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E= github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo= +github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI= +github.com/kr/pretty v0.3.0 h1:WgNl7dwNpEZ6jJ9k1snq4pZsg7DOEN8hP9Xw0Tsjwk0= +github.com/kr/pretty v0.3.0/go.mod h1:640gp4NfQd8pI5XOwp5fnNeVWj67G7CFk/SaSQn7NBk= github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ= github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI= +github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY= +github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE= github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0= github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= +github.com/rogpeppe/go-internal v1.6.1 h1:/FiVV8dS/e+YqF2JvO3yXRFbBLTIuSDkuC7aBOAvL+k= +github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc= github.com/sebdah/goldie/v2 v2.5.3 h1:9ES/mNN+HNUbNWpVAlrzuZ7jE+Nrczbj8uFRjM7624Y= github.com/sebdah/goldie/v2 v2.5.3/go.mod h1:oZ9fp0+se1eapSRjfYbsV/0Hqhbuu3bJVvKI/NNtssI= github.com/sergi/go-diff v1.0.0/go.mod h1:0CfEIISq7TuYL3j771MWULgwwjU+GofnZX9QAmXWZgo= @@ -75,7 +83,11 @@ golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU= golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk= +gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q= +gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI= gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI= gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY= gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ= diff --git a/apps/api/src/lib/go-html-to-md/html-to-markdown.go b/apps/api/src/lib/go-html-to-md/html-to-markdown.go index 474c8324..9905a69a 100644 --- a/apps/api/src/lib/go-html-to-md/html-to-markdown.go +++ b/apps/api/src/lib/go-html-to-md/html-to-markdown.go @@ -1,41 +1,25 @@ package main import ( - "flag" - "fmt" + "C" "log" - "sync" md "github.com/JohannesKaufmann/html-to-markdown" "github.com/JohannesKaufmann/html-to-markdown/plugin" ) -func convertHTMLToMarkdown(html string, wg *sync.WaitGroup, results chan<- string) { - defer wg.Done() +//export ConvertHTMLToMarkdown +func ConvertHTMLToMarkdown(html *C.char) *C.char { converter := md.NewConverter("", true, nil) converter.Use(plugin.GitHubFlavored()) - markdown, err := converter.ConvertString(html) + markdown, err := converter.ConvertString(C.GoString(html)) if err != nil { log.Fatal(err) } - results <- markdown + return C.CString(markdown) } func main() { - html := flag.String("html", "", "") - flag.Parse() - - var wg sync.WaitGroup - results := make(chan string, 1) - - wg.Add(1) - go convertHTMLToMarkdown(*html, &wg, results) - - wg.Wait() - close(results) - - for markdown := range results { - fmt.Println(markdown) - } + // This function is required for the main package } diff --git a/apps/api/src/lib/html-to-markdown.ts b/apps/api/src/lib/html-to-markdown.ts index 04fec4c6..4c7cffdd 100644 --- a/apps/api/src/lib/html-to-markdown.ts +++ b/apps/api/src/lib/html-to-markdown.ts @@ -1,108 +1,106 @@ -import { spawn } from 'node:child_process'; -import { join } from 'node:path'; +import koffi from 'koffi'; +import { join } from 'path'; +import "../services/sentry" +import * as Sentry from "@sentry/node"; + +import dotenv from 'dotenv'; +import { Logger } from './logger'; +dotenv.config(); export async function parseMarkdown(html: string): Promise { if (!html) { return ''; } - if (process.env.USE_GO_MARKDOWN_PARSER == "true") { - const goScriptPath = join(__dirname, 'go-html-to-md/html-to-markdown.go'); - const goModDir = join(__dirname, 'go-html-to-md'); - const child = spawn('go', ['run', goScriptPath, '--html', html], { - cwd: goModDir, - }); + try { + if (process.env.USE_GO_MARKDOWN_PARSER == "true") { + const goExecutablePath = join(__dirname, 'go-html-to-md/html-to-markdown.so'); + const lib = koffi.load(goExecutablePath); + + const convert = lib.func('Convert', 'string', ['string']); - return new Promise((resolve, reject) => { - let data = ''; - - child.stdout.on('data', (chunk) => { - data += chunk.toString(); // Convert Buffer to string + let markdownContent = await new Promise((resolve, reject) => { + convert.async(html, (err: Error, res: string) => { + if (err) { + reject(err); + } else { + resolve(res); + } + }); }); - child.stderr.on('data', (chunk) => { - reject(chunk.toString()); // Convert Buffer to string before rejecting - }); - - child.on('close', (code) => { - if (code === 0) { - resolve(data.trim()); - } else { - reject(new Error(`Process exited with code ${code}`)); - } - }); - }); - } else { - var TurndownService = require("turndown"); - var turndownPluginGfm = require('joplin-turndown-plugin-gfm') - - const turndownService = new TurndownService(); - turndownService.addRule("inlineLink", { - filter: function (node, options) { - return ( - options.linkStyle === "inlined" && - node.nodeName === "A" && - node.getAttribute("href") - ); - }, - replacement: function (content, node) { - var href = node.getAttribute("href").trim(); - var title = node.title ? ' "' + node.title + '"' : ""; - return "[" + content.trim() + "](" + href + title + ")\n"; - }, - }); - var gfm = turndownPluginGfm.gfm; - turndownService.use(gfm); - let markdownContent = ""; - const turndownPromise = new Promise((resolve, reject) => { - try { - const result = turndownService.turndown(html); - resolve(result); - } catch (error) { - reject("Error converting HTML to Markdown: " + error); - } - }); - - const timeoutPromise = new Promise((resolve, reject) => { - const timeout = 5000; // Timeout in milliseconds - setTimeout(() => reject("Conversion timed out after " + timeout + "ms"), timeout); - }); - - try { - markdownContent = await Promise.race([turndownPromise, timeoutPromise]); - } catch (error) { - console.error(error); - return ""; // Optionally return an empty string or handle the error as needed + markdownContent = processMultiLineLinks(markdownContent); + markdownContent = removeSkipToContentLinks(markdownContent); + return markdownContent; } + } catch (error) { + Sentry.captureException(error); + Logger.error(`Error converting HTML to Markdown with Go parser: ${error}`); + } - // multiple line links - let insideLinkContent = false; - let newMarkdownContent = ""; - let linkOpenCount = 0; - for (let i = 0; i < markdownContent.length; i++) { - const char = markdownContent[i]; + // Fallback to TurndownService if Go parser fails or is not enabled + var TurndownService = require("turndown"); + var turndownPluginGfm = require('joplin-turndown-plugin-gfm'); - if (char == "[") { - linkOpenCount++; - } else if (char == "]") { - linkOpenCount = Math.max(0, linkOpenCount - 1); - } - insideLinkContent = linkOpenCount > 0; + const turndownService = new TurndownService(); + turndownService.addRule("inlineLink", { + filter: function (node, options) { + return ( + options.linkStyle === "inlined" && + node.nodeName === "A" && + node.getAttribute("href") + ); + }, + replacement: function (content, node) { + var href = node.getAttribute("href").trim(); + var title = node.title ? ' "' + node.title + '"' : ""; + return "[" + content.trim() + "](" + href + title + ")\n"; + }, + }); + var gfm = turndownPluginGfm.gfm; + turndownService.use(gfm); - if (insideLinkContent && char == "\n") { - newMarkdownContent += "\\" + "\n"; - } else { - newMarkdownContent += char; - } - } - markdownContent = newMarkdownContent; + try { + let markdownContent = await turndownService.turndown(html); + markdownContent = processMultiLineLinks(markdownContent); + markdownContent = removeSkipToContentLinks(markdownContent); - // Remove [Skip to Content](#page) and [Skip to content](#skip) - markdownContent = markdownContent.replace( - /\[Skip to Content\]\(#[^\)]*\)/gi, - "" - ); return markdownContent; + } catch (error) { + console.error("Error converting HTML to Markdown: ", error); + return ""; // Optionally return an empty string or handle the error as needed } } + +function processMultiLineLinks(markdownContent: string): string { + let insideLinkContent = false; + let newMarkdownContent = ""; + let linkOpenCount = 0; + for (let i = 0; i < markdownContent.length; i++) { + const char = markdownContent[i]; + + if (char == "[") { + linkOpenCount++; + } else if (char == "]") { + linkOpenCount = Math.max(0, linkOpenCount - 1); + } + insideLinkContent = linkOpenCount > 0; + + if (insideLinkContent && char == "\n") { + newMarkdownContent += "\\" + "\n"; + } else { + newMarkdownContent += char; + } + } + return newMarkdownContent; +} + +function removeSkipToContentLinks(markdownContent: string): string { + // Remove [Skip to Content](#page) and [Skip to content](#skip) + const newMarkdownContent = markdownContent.replace( + /\[Skip to Content\]\(#[^\)]*\)/gi, + "" + ); + return newMarkdownContent; +} \ No newline at end of file diff --git a/apps/test-suite/tests/scrape.test.ts b/apps/test-suite/tests/scrape.test.ts index ec7b7202..8b2e15d1 100644 --- a/apps/test-suite/tests/scrape.test.ts +++ b/apps/test-suite/tests/scrape.test.ts @@ -31,6 +31,7 @@ describe("Scraping Checkup (E2E)", () => { describe("Scraping website tests with a dataset", () => { it("Should scrape the website and prompt it against OpenAI", async () => { + let totalTimeTaken = 0; let passedTests = 0; const batchSize = 15; // Adjusted to comply with the rate limit of 15 per minute const batchPromises = []; @@ -51,11 +52,16 @@ describe("Scraping Checkup (E2E)", () => { const batchPromise = Promise.all( batch.map(async (websiteData: WebsiteData) => { try { + const startTime = new Date().getTime(); const scrapedContent = await request(TEST_URL || "") - .post("/v0/scrape") + .post("/v1/scrape") .set("Content-Type", "application/json") .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`) - .send({ url: websiteData.website, pageOptions: { onlyMainContent: true } }); + .send({ url: websiteData.website }); + + const endTime = new Date().getTime(); + const timeTaken = endTime - startTime; + totalTimeTaken += timeTaken; if (scrapedContent.statusCode !== 200) { console.error(`Failed to scrape ${websiteData.website} ${scrapedContent.statusCode}`); @@ -165,6 +171,7 @@ describe("Scraping Checkup (E2E)", () => { const timeTaken = (endTime - startTime) / 1000; console.log(`Score: ${score}%`); console.log(`Total tokens: ${totalTokens}`); + console.log(`Total time taken: ${totalTimeTaken} miliseconds`); await logErrors(errorLog, timeTaken, totalTokens, score, websitesData.length); From ebf403548487249bdb2d8ca2bfe086f950736622 Mon Sep 17 00:00:00 2001 From: rafaelsideguide <150964962+rafaelsideguide@users.noreply.github.com> Date: Tue, 3 Sep 2024 13:15:21 -0300 Subject: [PATCH 3/5] added log so we can check --- apps/api/src/lib/html-to-markdown.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/apps/api/src/lib/html-to-markdown.ts b/apps/api/src/lib/html-to-markdown.ts index 4c7cffdd..e4f8f692 100644 --- a/apps/api/src/lib/html-to-markdown.ts +++ b/apps/api/src/lib/html-to-markdown.ts @@ -32,6 +32,7 @@ export async function parseMarkdown(html: string): Promise { markdownContent = processMultiLineLinks(markdownContent); markdownContent = removeSkipToContentLinks(markdownContent); + Logger.info(`HTML to Markdown conversion using Go parser successful`); return markdownContent; } } catch (error) { From d60fa6e0849fe13538cffaf36bafec55bc1c6ff6 Mon Sep 17 00:00:00 2001 From: rafaelsideguide <150964962+rafaelsideguide@users.noreply.github.com> Date: Tue, 3 Sep 2024 14:08:07 -0300 Subject: [PATCH 4/5] fixed dockerfile and function name. it's working --- apps/api/Dockerfile | 9 ++++----- apps/api/src/lib/html-to-markdown.ts | 6 +++++- 2 files changed, 9 insertions(+), 6 deletions(-) diff --git a/apps/api/Dockerfile b/apps/api/Dockerfile index a4a2c76b..527a6dc7 100644 --- a/apps/api/Dockerfile +++ b/apps/api/Dockerfile @@ -17,11 +17,11 @@ RUN pnpm install RUN --mount=type=secret,id=SENTRY_AUTH_TOKEN \ bash -c 'export SENTRY_AUTH_TOKEN="$(cat /run/secrets/SENTRY_AUTH_TOKEN)"; if [ -z $SENTRY_AUTH_TOKEN ]; then pnpm run build:nosentry; else pnpm run build; fi' -# Install Go 1.19 +# Install Go FROM golang:1.19 AS go-base COPY src/lib/go-html-to-md /app/src/lib/go-html-to-md -# Install Go dependencies and build +# Install Go dependencies and build parser lib RUN cd /app/src/lib/go-html-to-md && \ go mod tidy && \ go build -o html-to-markdown.so -buildmode=c-shared html-to-markdown.go && \ @@ -33,9 +33,8 @@ RUN apt-get update -qq && \ rm -rf /var/lib/apt/lists /var/cache/apt/archives COPY --from=prod-deps /app/node_modules /app/node_modules COPY --from=build /app /app -COPY --from=go-base /app/src/lib/go-html-to-md/html-to-markdown.so /app/src/lib/go-html-to-md/html-to-markdown.so - +COPY --from=go-base /app/src/lib/go-html-to-md/html-to-markdown.so /app/dist/src/lib/go-html-to-md/html-to-markdown.so # Start the server by default, this can be overwritten at runtime EXPOSE 8080 -ENV PUPPETEER_EXECUTABLE_PATH="/usr/bin/chromium" +ENV PUPPETEER_EXECUTABLE_PATH="/usr/bin/chromium" \ No newline at end of file diff --git a/apps/api/src/lib/html-to-markdown.ts b/apps/api/src/lib/html-to-markdown.ts index e4f8f692..a5f69962 100644 --- a/apps/api/src/lib/html-to-markdown.ts +++ b/apps/api/src/lib/html-to-markdown.ts @@ -8,6 +8,10 @@ import dotenv from 'dotenv'; import { Logger } from './logger'; dotenv.config(); +// TODO: test with invalid html +// TODO: create a singleton for the converter +// TODO: add a timeout to the Go parser + export async function parseMarkdown(html: string): Promise { if (!html) { return ''; @@ -18,7 +22,7 @@ export async function parseMarkdown(html: string): Promise { const goExecutablePath = join(__dirname, 'go-html-to-md/html-to-markdown.so'); const lib = koffi.load(goExecutablePath); - const convert = lib.func('Convert', 'string', ['string']); + const convert = lib.func('ConvertHTMLToMarkdown', 'string', ['string']); let markdownContent = await new Promise((resolve, reject) => { convert.async(html, (err: Error, res: string) => { From c5e1d77a8253e471a7b021229ac6c85743ba8343 Mon Sep 17 00:00:00 2001 From: rafaelsideguide <150964962+rafaelsideguide@users.noreply.github.com> Date: Tue, 3 Sep 2024 15:21:45 -0300 Subject: [PATCH 5/5] added invalid html tests --- apps/api/src/lib/__tests__/html-to-markdown.test.ts | 13 ++++++++++++- apps/api/src/lib/html-to-markdown.ts | 1 - 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/apps/api/src/lib/__tests__/html-to-markdown.test.ts b/apps/api/src/lib/__tests__/html-to-markdown.test.ts index 00db7758..3c68c959 100644 --- a/apps/api/src/lib/__tests__/html-to-markdown.test.ts +++ b/apps/api/src/lib/__tests__/html-to-markdown.test.ts @@ -25,5 +25,16 @@ describe('parseMarkdown', () => { await expect(parseMarkdown(html)).resolves.toBe(expectedMarkdown); }); - + it('should handle various types of invalid HTML gracefully', async () => { + const invalidHtmls = [ + { html: '

Unclosed tag', expected: 'Unclosed tag' }, + { html: '