Merge pull request #121 from thecodingmachine/rpcc_message_too_large

PrintToPDF: rpcc: message too large
gotenberg · Oct 7, 2019 · cd8d2b5 · cd8d2b5
2 parents fa9963a + 8d89b2e
commit cd8d2b5
Show file tree

Hide file tree

Showing 11 changed files with 416 additions and 53 deletions.
diff --git a/Makefile b/Makefile
@@ -15,6 +15,7 @@ DEFAULT_LISTEN_PORT=3000
 DISABLE_GOOGLE_CHROME=0
 DISABLE_UNOCONV=0
 LOG_LEVEL=INFO
+DEFAULT_GOOGLE_CHROME_RPCC_BUFFER_SIZE=1048576
 
 # build the base Docker image.
 base:
@@ -54,7 +55,7 @@ image:
 
 # start the API using previously built Docker image.
 gotenberg:
-	docker run -it --rm -e MAXIMUM_WAIT_TIMEOUT=$(MAXIMUM_WAIT_TIMEOUT) -e MAXIMUM_WAIT_DELAY=$(MAXIMUM_WAIT_DELAY) -e MAXIMUM_WEBHOOK_URL_TIMEOUT=$(MAXIMUM_WEBHOOK_URL_TIMEOUT) -e DEFAULT_WEBHOOK_URL_TIMEOUT=$(DEFAULT_WEBHOOK_URL_TIMEOUT) -e MAXIMUM_WEBHOOK_URL_TIMEOUT=$(MAXIMUM_WEBHOOK_URL_TIMEOUT) -e DEFAULT_LISTEN_PORT=$(DEFAULT_LISTEN_PORT) -e DISABLE_GOOGLE_CHROME=$(DISABLE_GOOGLE_CHROME) -e DISABLE_UNOCONV=$(DISABLE_UNOCONV) -e LOG_LEVEL=$(LOG_LEVEL)  -p "$(DEFAULT_LISTEN_PORT):$(DEFAULT_LISTEN_PORT)" $(DOCKER_REPOSITORY)/gotenberg:$(VERSION)
+	docker run -it --rm -e MAXIMUM_WAIT_TIMEOUT=$(MAXIMUM_WAIT_TIMEOUT) -e MAXIMUM_WAIT_DELAY=$(MAXIMUM_WAIT_DELAY) -e MAXIMUM_WEBHOOK_URL_TIMEOUT=$(MAXIMUM_WEBHOOK_URL_TIMEOUT) -e DEFAULT_WEBHOOK_URL_TIMEOUT=$(DEFAULT_WEBHOOK_URL_TIMEOUT) -e MAXIMUM_WEBHOOK_URL_TIMEOUT=$(MAXIMUM_WEBHOOK_URL_TIMEOUT) -e DEFAULT_LISTEN_PORT=$(DEFAULT_LISTEN_PORT) -e DISABLE_GOOGLE_CHROME=$(DISABLE_GOOGLE_CHROME) -e DISABLE_UNOCONV=$(DISABLE_UNOCONV) -e LOG_LEVEL=$(LOG_LEVEL) -e DEFAULT_GOOGLE_CHROME_RPCC_BUFFER_SIZE=$(DEFAULT_GOOGLE_CHROME_RPCC_BUFFER_SIZE)  -p "$(DEFAULT_LISTEN_PORT):$(DEFAULT_LISTEN_PORT)" $(DOCKER_REPOSITORY)/gotenberg:$(VERSION)
 
 # publish Gotenberg images according to version.
 publish:

diff --git a/build/docs/content/03-environment-variables.md b/build/docs/content/03-environment-variables.md
@@ -33,6 +33,19 @@ It takes the strings `"0"` or `"1"` as value where `1` means `true`
 > If Google Chrome is disabled, the following conversions will **not** be available anymore:
 > [HTML](#html), [URL](#url) and [Markdown](#markdown)
 
+## Default Google Chrome rpcc buffer size
+
+When performing a [HTML](#html), [URL](#url) or [Markdown](#markdown) conversion, the API might return
+a `400` HTTP code with the message `increase the Google Chrome rpcc buffer size`.
+
+If so, you may increase this buffer size with the environment variable `DEFAULT_GOOGLE_CHROME_RPCC_BUFFER_SIZE`.
+
+It takes a string representation of an int as value (e.g. `"1048576"` for 1 MB).
+The hard limit is 100 MB and is defined by Google Chrome itself.
+
+> The default Google Chrome rpcc buffer size may also be overridden per request thanks to the form field `googleChromeRpccBufferSize`.
+> See the [rpcc buffer size section](#html.rpcc_buffer_size).
+
 ## Disable LibreOffice (unoconv)
 
 You may also disable LibreOffice (unoconv) with `DISABLE_UNOCONV`.

diff --git a/build/docs/content/04-html.md b/build/docs/content/04-html.md
@@ -347,3 +347,55 @@ $request->setWaitDelay(5.5);
 $dest = "result.pdf";
 $client->store($request, $dest);
 ```
+
+## Rpcc buffer size
+
+The API might return a `400` HTTP code with the message `increase the Google Chrome rpcc buffer size`.
+
+If so, you may increase this buffer size with a form field named `googleChromeRpccBufferSize`.
+
+It takes an int as value (e.g. `1048576` for 1 MB).
+The hard limit is 100 MB and is defined by Google Chrome itself.
+
+> You may also define this value globally: see the [environment variables](#environment_variables.default_google_chrome_rpcc_buffer_size) section.
+
+### cURL
+
+```bash
+$ curl --request POST \
+    --url http://localhost:3000/convert/html \
+    --header 'Content-Type: multipart/form-data' \
+    --form files=@index.html \
+    --form googleChromeRpccBufferSize=1048576 \
+    -o result.pdf
+```
+
+### Go
+
+```golang
+import "github.com/thecodingmachine/gotenberg-go-client/v6"
+
+func main() {
+    c := &gotenberg.Client{Hostname: "http://localhost:3000"}
+    req, _ := gotenberg.NewHTMLRequest("index.html")
+    req.GoogleChromeRpccBufferSize(1048576)
+    dest := "result.pdf"
+    c.Store(req, dest)
+}
+```
+
+### PHP
+
+```php
+use TheCodingMachine\Gotenberg\Client;
+use TheCodingMachine\Gotenberg\DocumentFactory;
+use TheCodingMachine\Gotenberg\HTMLRequest;
+use TheCodingMachine\Gotenberg\Request;
+
+$client = new Client('http://localhost:3000', new \Http\Adapter\Guzzle6\Client());
+$index = DocumentFactory::makeFromPath('index.html', 'index.html');
+$request = new HTMLRequest($index);
+$request->setGoogleChromeRpccBufferSize(1048576);
+$dest = "result.pdf";
+$client->store($request, $dest);
+```
diff --git a/docs/index.html b/docs/index.html
@@ -263,6 +263,23 @@ <h2 class="Heading"><a class="Anchor" aria-hidden="true" id="environment_variabl
 <a href="#html">HTML</a>, <a href="#url">URL</a> and <a href="#markdown">Markdown</a></p>
 </blockquote>
 
+<h2 class="Heading"><a class="Anchor" aria-hidden="true" id="environment_variables.default_google_chrome_rpcc_buffer_size" href="#environment_variables.default_google_chrome_rpcc_buffer_size">
+	<svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather feather-link"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg>
+</a>Default Google Chrome rpcc buffer size</h2>
+
+<p>When performing a <a href="#html">HTML</a>, <a href="#url">URL</a> or <a href="#markdown">Markdown</a> conversion, the API might return
+a <code>400</code> HTTP code with the message <code>increase the Google Chrome rpcc buffer size</code>.</p>
+
+<p>If so, you may increase this buffer size with the environment variable <code>DEFAULT_GOOGLE_CHROME_RPCC_BUFFER_SIZE</code>.</p>
+
+<p>It takes a string representation of an int as value (e.g. <code>&#34;1048576&#34;</code> for 1 MB).
+The hard limit is 100 MB and is defined by Google Chrome itself.</p>
+
+<blockquote>
+<p>The default Google Chrome rpcc buffer size may also be overridden per request thanks to the form field <code>googleChromeRpccBufferSize</code>.
+See the <a href="#html.rpcc_buffer_size">rpcc buffer size section</a>.</p>
+</blockquote>
+
 <h2 class="Heading"><a class="Anchor" aria-hidden="true" id="environment_variables.disable_libre_office_unoconv" href="#environment_variables.disable_libre_office_unoconv">
 	<svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather feather-link"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg>
 </a>Disable LibreOffice (unoconv)</h2>
@@ -724,6 +741,65 @@ <h3 class="Heading"><a class="Anchor" aria-hidden="true" id="html.wait_delay.php
 $request-&gt;setWaitDelay(5.5);
 $dest = &#34;result.pdf&#34;;
 $client-&gt;store($request, $dest);
+</pre>
+
+<h2 class="Heading"><a class="Anchor" aria-hidden="true" id="html.rpcc_buffer_size" href="#html.rpcc_buffer_size">
+	<svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather feather-link"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg>
+</a>Rpcc buffer size</h2>
+
+<p>The API might return a <code>400</code> HTTP code with the message <code>increase the Google Chrome rpcc buffer size</code>.</p>
+
+<p>If so, you may increase this buffer size with a form field named <code>googleChromeRpccBufferSize</code>.</p>
+
+<p>It takes an int as value (e.g. <code>1048576</code> for 1 MB).
+The hard limit is 100 MB and is defined by Google Chrome itself.</p>
+
+<blockquote>
+<p>You may also define this value globally: see the <a href="#environment_variables.default_google_chrome_rpcc_buffer_size">environment variables</a> section.</p>
+</blockquote>
+
+<h3 class="Heading"><a class="Anchor" aria-hidden="true" id="html.rpcc_buffer_size.c_url" href="#html.rpcc_buffer_size.c_url">
+	<svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather feather-link"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg>
+</a>cURL</h3>
+
+<pre class="chroma">$ curl --request POST <span class="se">\
+</span><span class="se"></span>    --url http://localhost:3000/convert/html <span class="se">\
+</span><span class="se"></span>    --header <span class="s1">&#39;Content-Type: multipart/form-data&#39;</span> <span class="se">\
+</span><span class="se"></span>    --form <span class="nv">files</span><span class="o">=</span>@index.html <span class="se">\
+</span><span class="se"></span>    --form <span class="nv">googleChromeRpccBufferSize</span><span class="o">=</span><span class="m">1048576</span> <span class="se">\
+</span><span class="se"></span>    -o result.pdf
+</pre>
+
+<h3 class="Heading"><a class="Anchor" aria-hidden="true" id="html.rpcc_buffer_size.go" href="#html.rpcc_buffer_size.go">
+	<svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather feather-link"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg>
+</a>Go</h3>
+
+<pre class="chroma"><span class="kn">import</span> <span class="s">&#34;github.com/thecodingmachine/gotenberg-go-client/v6&#34;</span>
+
+<span class="kd">func</span> <span class="nf">main</span><span class="p">()</span> <span class="p">{</span>
+    <span class="nx">c</span> <span class="o">:=</span> <span class="o">&amp;</span><span class="nx">gotenberg</span><span class="p">.</span><span class="nx">Client</span><span class="p">{</span><span class="nx">Hostname</span><span class="p">:</span> <span class="s">&#34;http://localhost:3000&#34;</span><span class="p">}</span>
+    <span class="nx">req</span><span class="p">,</span> <span class="nx">_</span> <span class="o">:=</span> <span class="nx">gotenberg</span><span class="p">.</span><span class="nf">NewHTMLRequest</span><span class="p">(</span><span class="s">&#34;index.html&#34;</span><span class="p">)</span>
+    <span class="nx">req</span><span class="p">.</span><span class="nf">GoogleChromeRpccBufferSize</span><span class="p">(</span><span class="mi">1048576</span><span class="p">)</span>
+    <span class="nx">dest</span> <span class="o">:=</span> <span class="s">&#34;result.pdf&#34;</span>
+    <span class="nx">c</span><span class="p">.</span><span class="nf">Store</span><span class="p">(</span><span class="nx">req</span><span class="p">,</span> <span class="nx">dest</span><span class="p">)</span>
+<span class="p">}</span>
+</pre>
+
+<h3 class="Heading"><a class="Anchor" aria-hidden="true" id="html.rpcc_buffer_size.php" href="#html.rpcc_buffer_size.php">
+	<svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather feather-link"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg>
+</a>PHP</h3>
+
+<pre class="chroma">use TheCodingMachine\Gotenberg\Client;
+use TheCodingMachine\Gotenberg\DocumentFactory;
+use TheCodingMachine\Gotenberg\HTMLRequest;
+use TheCodingMachine\Gotenberg\Request;
+
+$client = new Client(&#39;http://localhost:3000&#39;, new \Http\Adapter\Guzzle6\Client());
+$index = DocumentFactory::makeFromPath(&#39;index.html&#39;, &#39;index.html&#39;);
+$request = new HTMLRequest($index);
+$request-&gt;setGoogleChromeRpccBufferSize(1048576);
+$dest = &#34;result.pdf&#34;;
+$client-&gt;store($request, $dest);
 </pre>
 
               </div>

diff --git a/internal/app/xhttp/handler_test.go b/internal/app/xhttp/handler_test.go
@@ -184,6 +184,24 @@ func TestHTMLHandler(t *testing.T) {
 	req = httptest.NewRequest(http.MethodPost, endpoint, body)
 	req.Header.Set(echo.HeaderContentType, contentType)
 	test.AssertStatusCode(t, http.StatusBadRequest, srv, req)
+	// should return 400 as "googleChromeRpccBufferSize" form field
+	// value is < 0.
+	body, contentType = test.HTMLMultipartForm(t, map[string]string{string(resource.GoogleChromeRpccBufferSizeArgKey): "-1"})
+	req = httptest.NewRequest(http.MethodPost, endpoint, body)
+	req.Header.Set(echo.HeaderContentType, contentType)
+	test.AssertStatusCode(t, http.StatusBadRequest, srv, req)
+	// should return 400 as "googleChromeRpccBufferSize" form field
+	// value is is > config.MaximumGoogleChromeRpccBufferSize().
+	body, contentType = test.HTMLMultipartForm(t, map[string]string{string(resource.GoogleChromeRpccBufferSizeArgKey): "104857601"})
+	req = httptest.NewRequest(http.MethodPost, endpoint, body)
+	req.Header.Set(echo.HeaderContentType, contentType)
+	test.AssertStatusCode(t, http.StatusBadRequest, srv, req)
+	// should return 400 as "googleChromeRpccBufferSize" form field
+	// value is invalid.
+	body, contentType = test.HTMLMultipartForm(t, map[string]string{string(resource.GoogleChromeRpccBufferSizeArgKey): "not an int"})
+	req = httptest.NewRequest(http.MethodPost, endpoint, body)
+	req.Header.Set(echo.HeaderContentType, contentType)
+	test.AssertStatusCode(t, http.StatusBadRequest, srv, req)
 }
 
 func TestURLHandler(t *testing.T) {
@@ -314,6 +332,24 @@ func TestURLHandler(t *testing.T) {
 	req = httptest.NewRequest(http.MethodPost, endpoint, body)
 	req.Header.Set(echo.HeaderContentType, contentType)
 	test.AssertStatusCode(t, http.StatusBadRequest, srv, req)
+	// should return 400 as "googleChromeRpccBufferSize" form field
+	// value is < 0.
+	body, contentType = test.URLMultipartForm(t, map[string]string{string(resource.GoogleChromeRpccBufferSizeArgKey): "-1"})
+	req = httptest.NewRequest(http.MethodPost, endpoint, body)
+	req.Header.Set(echo.HeaderContentType, contentType)
+	test.AssertStatusCode(t, http.StatusBadRequest, srv, req)
+	// should return 400 as "googleChromeRpccBufferSize" form field
+	// value is is > config.MaximumGoogleChromeRpccBufferSize().
+	body, contentType = test.URLMultipartForm(t, map[string]string{string(resource.GoogleChromeRpccBufferSizeArgKey): "104857601"})
+	req = httptest.NewRequest(http.MethodPost, endpoint, body)
+	req.Header.Set(echo.HeaderContentType, contentType)
+	test.AssertStatusCode(t, http.StatusBadRequest, srv, req)
+	// should return 400 as "googleChromeRpccBufferSize" form field
+	// value is invalid.
+	body, contentType = test.URLMultipartForm(t, map[string]string{string(resource.GoogleChromeRpccBufferSizeArgKey): "not an int"})
+	req = httptest.NewRequest(http.MethodPost, endpoint, body)
+	req.Header.Set(echo.HeaderContentType, contentType)
+	test.AssertStatusCode(t, http.StatusBadRequest, srv, req)
 }
 
 func TestMarkdownHandler(t *testing.T) {
@@ -444,6 +480,24 @@ func TestMarkdownHandler(t *testing.T) {
 	req = httptest.NewRequest(http.MethodPost, endpoint, body)
 	req.Header.Set(echo.HeaderContentType, contentType)
 	test.AssertStatusCode(t, http.StatusBadRequest, srv, req)
+	// should return 400 as "googleChromeRpccBufferSize" form field
+	// value is < 0.
+	body, contentType = test.MarkdownMultipartForm(t, map[string]string{string(resource.GoogleChromeRpccBufferSizeArgKey): "-1"})
+	req = httptest.NewRequest(http.MethodPost, endpoint, body)
+	req.Header.Set(echo.HeaderContentType, contentType)
+	test.AssertStatusCode(t, http.StatusBadRequest, srv, req)
+	// should return 400 as "googleChromeRpccBufferSize" form field
+	// value is is > config.MaximumGoogleChromeRpccBufferSize().
+	body, contentType = test.MarkdownMultipartForm(t, map[string]string{string(resource.GoogleChromeRpccBufferSizeArgKey): "104857601"})
+	req = httptest.NewRequest(http.MethodPost, endpoint, body)
+	req.Header.Set(echo.HeaderContentType, contentType)
+	test.AssertStatusCode(t, http.StatusBadRequest, srv, req)
+	// should return 400 as "googleChromeRpccBufferSize" form field
+	// value is invalid.
+	body, contentType = test.MarkdownMultipartForm(t, map[string]string{string(resource.GoogleChromeRpccBufferSizeArgKey): "not an int"})
+	req = httptest.NewRequest(http.MethodPost, endpoint, body)
+	req.Header.Set(echo.HeaderContentType, contentType)
+	test.AssertStatusCode(t, http.StatusBadRequest, srv, req)
 }
 
 func TestOfficeHandler(t *testing.T) {

diff --git a/internal/app/xhttp/option.go b/internal/app/xhttp/option.go
@@ -48,18 +48,23 @@ func chromePrinterOptions(r resource.Resource, config conf.Config) (printer.Chro
 		if err != nil {
 			return printer.ChromePrinterOptions{}, err
 		}
+		googleChromeRpccBufferSize, err := resource.GoogleChromeRpccBufferSizeArg(r, config)
+		if err != nil {
+			return printer.ChromePrinterOptions{}, err
+		}
 		return printer.ChromePrinterOptions{
-			WaitTimeout:  waitTimeout,
-			WaitDelay:    waitDelay,
-			HeaderHTML:   headerHTML,
-			FooterHTML:   footerHTML,
-			PaperWidth:   paperWidth,
-			PaperHeight:  paperHeight,
-			MarginTop:    marginTop,
-			MarginBottom: marginBottom,
-			MarginLeft:   marginLeft,
-			MarginRight:  marginRight,
-			Landscape:    landscape,
+			WaitTimeout:    waitTimeout,
+			WaitDelay:      waitDelay,
+			HeaderHTML:     headerHTML,
+			FooterHTML:     footerHTML,
+			PaperWidth:     paperWidth,
+			PaperHeight:    paperHeight,
+			MarginTop:      marginTop,
+			MarginBottom:   marginBottom,
+			MarginLeft:     marginLeft,
+			MarginRight:    marginRight,
+			Landscape:      landscape,
+			RpccBufferSize: googleChromeRpccBufferSize,
 		}, nil
 	}
 	opts, err := resolver()

diff --git a/internal/app/xhttp/pkg/resource/arg.go b/internal/app/xhttp/pkg/resource/arg.go
@@ -51,6 +51,9 @@ const (
 	// LandscapeArgKey is the key
 	// of the argument "landscape".
 	LandscapeArgKey ArgKey = "landscape"
+	// GoogleChromeRpccBufferSizeArgKey is the key
+	// of the argument "googleChromeRpccBufferSize".
+	GoogleChromeRpccBufferSizeArgKey ArgKey = "googleChromeRpccBufferSize"
 )
 
 /*
@@ -73,6 +76,7 @@ func ArgKeys() []ArgKey {
 		MarginLeftArgKey,
 		MarginRightArgKey,
 		LandscapeArgKey,
+		GoogleChromeRpccBufferSizeArgKey,
 	}
 }
 
@@ -265,3 +269,24 @@ func MarginArgs(r Resource, config conf.Config) (float64, float64, float64, floa
 		marginRight,
 		nil
 }
+
+/*
+GoogleChromeRpccBufferSizeArg is a helper for retrieving
+the "googleChromeRpccBufferSize" argument as int64.
+
+It also validates it against the application
+configuration.
+*/
+func GoogleChromeRpccBufferSizeArg(r Resource, config conf.Config) (int64, error) {
+	const op string = "resource.GoogleChromeRpccBufferSizeArg"
+	result, err := r.Int64Arg(
+		GoogleChromeRpccBufferSizeArgKey,
+		config.DefaultGoogleChromeRpccBufferSize(),
+		xassert.Int64NotInferiorTo(0.0),
+		xassert.Int64NotSuperiorTo(config.MaximumGoogleChromeRpccBufferSize()),
+	)
+	if err != nil {
+		return result, xerror.New(op, err)
+	}
+	return result, nil
+}