markup: add --citeproc to pandoc converter

docs/content/en/content-management/formats.md

@@ -43,7 +43,7 @@ Hugo passes reasonable default arguments to these external helpers by default:
 
 - `asciidoctor`: `--no-header-footer -`
 - `rst2html`: `--leave-comments --initial-header-level=2`
-- `pandoc`: `--mathjax`
+- `pandoc`: `--mathjax` and, for pandoc >= 2.11, `--citeproc`
 
 {{% note %}}
 Because additional formats are external commands, generation performance will rely heavily on the performance of the external tool you are using. As this feature is still in its infancy, feedback is welcome.
@@ -106,7 +106,59 @@ parameters. Run Hugo with `-v`. You will get an output like
 INFO 2019/12/22 09:08:48 Rendering book-as-pdf.adoc with C:\Ruby26-x64\bin\asciidoctor.bat using asciidoc args [--no-header-footer -r asciidoctor-html5s -b html5s -r asciidoctor-diagram --base-dir D:\prototypes\hugo_asciidoc_ddd\docs -a outdir=D:\prototypes\hugo_asciidoc_ddd\build -] ...
 ```
 
-## Learn markdown
+### External Helper Pandoc
+
+[Pandoc](https://pandoc.org) is a universal document converter and can be used to convert markdown files.
+In Hugo, Pandoc can be used for LaTeX-style math (the `--mathjax` command line option is provided):
+
+```
+---
+title: Math document
+---
+
+Some inline math: $a^2 + b^2 = c^2$.
+```
+
+This will render in your HTML as:
+
+```
+<p>Some inline math: <span class="math inline">\(a^2 + b^2 = c^2\)</span></p>
+```
+You will have to [add MathJax](https://www.mathjax.org/#gettingstarted) to your template to properly render the math.
+
+For **Pandoc >= 2.11**, you can use [citations](https://pandoc.org/MANUAL.html#extension-citations).
+One way is to employ [BibTeX files](https://en.wikibooks.org/wiki/LaTeX/Bibliography_Management#BibTeX) to cite:
+
+```
+---
+title: Citation document
+---
+---
+bibliography: assets/bibliography.bib
+...
+This is a citation: @Doe2022
+```
+
+Note that Hugo will **not** pass its metadata YAML block to Pandoc; however, it will pass the **second** meta data block, denoted with `---` and `...` to Pandoc.
+Thus, all Pandoc settings should go there.
+
+You can also add all elements from a bibliography file (without citing them explicitly) using:
+
+```
+---
+title: My Publications
+---
+---
+bibliography: assets/bibliography.bib
+nocite: |
+  @*
+...
+```
+
+It is also possible to provide a custom [CSL style](https://citationstyles.org/authors/) by passing `csl: path-to-style.csl` as a Pandoc option.
+
+
+## Learn Markdown
 
 Markdown syntax is simple enough to learn in a single sitting. The following are excellent resources to get you up and running:
 

markup/pandoc/convert.go

@@ -15,10 +15,14 @@
 package pandoc
 
 import (
+	"bytes"
+	"strconv"
+	"strings"
+	"sync"
+
 	"github.com/gohugoio/hugo/common/hexec"
 	"github.com/gohugoio/hugo/htesting"
 	"github.com/gohugoio/hugo/identity"
-
 	"github.com/gohugoio/hugo/markup/converter"
 	"github.com/gohugoio/hugo/markup/internal"
 )
@@ -65,6 +69,9 @@ func (c *pandocConverter) getPandocContent(src []byte, ctx converter.DocumentCon
 		return src, nil
 	}
 	args := []string{"--mathjax"}
+	if supportsCitations(c.cfg) {
+		args = append(args[:], "--citeproc")
+	}
 	return internal.ExternallyRenderContent(c.cfg, ctx, src, binaryName, args)
 }
 
@@ -77,6 +84,69 @@ func getPandocBinaryName() string {
 	return ""
 }
 
+type pandocVersion struct {
+	major, minor int64
+}
+
+func (left pandocVersion) greaterThanOrEqual(right pandocVersion) bool {
+	return left.major > right.major || (left.major == right.major && left.minor >= right.minor)
+}
+
+var versionOnce sync.Once
+var foundPandocVersion pandocVersion
+
+// getPandocVersion parses the pandoc version output
+func getPandocVersion(cfg converter.ProviderConfig) (pandocVersion, error) {
+	var err error
+
+	versionOnce.Do(func() {
+		argsv := []any{"--version"}
+
+		var out bytes.Buffer
+		argsv = append(argsv, hexec.WithStdout(&out))
+
+		cmd, err := cfg.Exec.New(pandocBinary, argsv...)
+		if err != nil {
+			cfg.Logger.Errorf("Could not call pandoc: %v", err)
+			foundPandocVersion = pandocVersion{0, 0}
+			return
+		}
+
+		err = cmd.Run()
+		if err != nil {
+			cfg.Logger.Errorf("%s --version: %v", pandocBinary, err)
+			foundPandocVersion = pandocVersion{0, 0}
+			return
+		}
+
+		outbytes := bytes.Replace(out.Bytes(), []byte("\r"), []byte(""), -1)
+		output := strings.Split(string(outbytes), "\n")[0]
+		// Split, e.g., "pandoc 2.5" into 2 and 5 and convert them to integers
+		versionStrings := strings.Split(strings.Split(output, " ")[1], ".")
+		majorVersion, err := strconv.ParseInt(versionStrings[0], 10, 64)
+		if err != nil {
+			println(err)
+		}
+		minorVersion, err := strconv.ParseInt(versionStrings[1], 10, 64)
+		if err != nil {
+			println(err)
+		}
+		foundPandocVersion = pandocVersion{majorVersion, minorVersion}
+	})
+
+	return foundPandocVersion, err
+}
+
+// SupportsCitations returns true for pandoc versions >= 2.11, which include citeproc
+func supportsCitations(cfg converter.ProviderConfig) bool {
+	if Supports() {
+		foundPandocVersion, err := getPandocVersion(cfg)
+		supportsCitations := foundPandocVersion.greaterThanOrEqual(pandocVersion{2, 11}) && err == nil
+		return supportsCitations
+	}
+	return false
+}
+
 // Supports returns whether Pandoc is installed on this computer.
 func Supports() bool {
 	hasBin := getPandocBinaryName() != ""

markup/pandoc/convert_test.go

@@ -25,7 +25,7 @@ import (
 	qt "github.com/frankban/quicktest"
 )
 
-func TestConvert(t *testing.T) {
+func setupTestConverter(t *testing.T) (*qt.C, converter.Converter, converter.ProviderConfig) {
 	if !Supports() {
 		t.Skip("pandoc not installed")
 	}
@@ -38,7 +38,140 @@ func TestConvert(t *testing.T) {
 	c.Assert(err, qt.IsNil)
 	conv, err := p.New(converter.DocumentContext{})
 	c.Assert(err, qt.IsNil)
-	b, err := conv.Convert(converter.RenderContext{Src: []byte("testContent")})
+	return c, conv, cfg
+}
+
+func TestConvert(t *testing.T) {
+	c, conv, _ := setupTestConverter(t)
+	output, err := conv.Convert(converter.RenderContext{Src: []byte("testContent")})
+	c.Assert(err, qt.IsNil)
+	c.Assert(string(output.Bytes()), qt.Equals, "<p>testContent</p>\n")
+}
+
+func runCiteprocTest(t *testing.T, content string, expected string) {
+	c, conv, cfg := setupTestConverter(t)
+	if !supportsCitations(cfg) {
+		t.Skip("pandoc does not support citations")
+	}
+	output, err := conv.Convert(converter.RenderContext{Src: []byte(content)})
 	c.Assert(err, qt.IsNil)
-	c.Assert(string(b.Bytes()), qt.Equals, "<p>testContent</p>\n")
+	c.Assert(string(output.Bytes()), qt.Equals, expected)
+}
+
+func TestGetPandocVersionCallTwice(t *testing.T) {
+	c, _, cfg := setupTestConverter(t)
+
+	version1, err1 := getPandocVersion(cfg)
+	version2, err2 := getPandocVersion(cfg)
+	c.Assert(version1, qt.Equals, version2)
+	c.Assert(err1, qt.IsNil)
+	c.Assert(err2, qt.IsNil)
+}
+
+func TestPandocVersionEquality(t *testing.T) {
+	c := qt.New(t)
+	v1 := pandocVersion{1, 0}
+	v2 := pandocVersion{2, 0}
+	v3 := pandocVersion{2, 2}
+	v4 := pandocVersion{1, 2}
+	v5 := pandocVersion{2, 11}
+
+	// 1 >= 1 -> true
+	c.Assert(v1.greaterThanOrEqual(v1), qt.IsTrue)
+
+	// 1 >= 2 -> false, 2 >= 1 -> tru
+	c.Assert(v1.greaterThanOrEqual(v2), qt.IsFalse)
+	c.Assert(v2.greaterThanOrEqual(v1), qt.IsTrue)
+
+	// 2.0 >= 2.2 -> false, 2.2 >= 2.0 -> true
+	c.Assert(v2.greaterThanOrEqual(v3), qt.IsFalse)
+	c.Assert(v3.greaterThanOrEqual(v2), qt.IsTrue)
+
+	// 2.2 >= 1.2 -> true, 1.2 >= 2.2 -> false
+	c.Assert(v3.greaterThanOrEqual(v4), qt.IsTrue)
+	c.Assert(v4.greaterThanOrEqual(v3), qt.IsFalse)
+
+	// 2.11 >= 2.2 -> true, 2.2 >= 2.11 -> false
+	c.Assert(v5.greaterThanOrEqual(v3), qt.IsTrue)
+	c.Assert(v3.greaterThanOrEqual(v5), qt.IsFalse)
+}
+
+func TestCiteprocWithHugoMeta(t *testing.T) {
+	content := `
+---
+title: Test
+published: 2022-05-30
+---
+testContent
+`
+	expected := "<p>testContent</p>\n"
+	runCiteprocTest(t, content, expected)
+}
+
+func TestCiteprocWithPandocMeta(t *testing.T) {
+	content := `
+---
+---
+---
+...
+testContent
+`
+	expected := "<p>testContent</p>\n"
+	runCiteprocTest(t, content, expected)
+}
+
+func TestCiteprocWithBibliography(t *testing.T) {
+	content := `
+---
+---
+---
+bibliography: testdata/bibliography.bib
+...
+testContent
+`
+	expected := "<p>testContent</p>\n"
+	runCiteprocTest(t, content, expected)
+}
+
+func TestCiteprocWithExplicitCitation(t *testing.T) {
+	content := `
+---
+---
+---
+bibliography: testdata/bibliography.bib
+...
+@Doe2022
+`
+	expected := `<p><span class="citation" data-cites="Doe2022">Doe and Mustermann
+(2022)</span></p>
+<div id="refs" class="references csl-bib-body hanging-indent"
+role="doc-bibliography">
+<div id="ref-Doe2022" class="csl-entry" role="doc-biblioentry">
+Doe, Jane, and Max Mustermann. 2022. <span>“A Treatise on Hugo
+Tests.”</span> <em>Hugo Websites</em>.
+</div>
+</div>
+`
+	runCiteprocTest(t, content, expected)
+}
+
+func TestCiteprocWithNocite(t *testing.T) {
+	content := `
+---
+---
+---
+bibliography: testdata/bibliography.bib
+nocite: |
+  @*
+...
+`
+	expected := `<div id="refs" class="references csl-bib-body hanging-indent"
+role="doc-bibliography">
+<div id="ref-Doe2022" class="csl-entry" role="doc-biblioentry">
+Doe, Jane, and Max Mustermann. 2022. <span>“A Treatise on Hugo
+Tests.”</span> <em>Hugo Websites</em>.
+</div>
+</div>
+`
+	runCiteprocTest(t, content, expected)
 }

markup/pandoc/testdata/bibliography.bib

@@ -0,0 +1,6 @@
+@article{Doe2022,
+    author    = "Jane Doe and Max Mustermann",
+    title     = "A Treatise on Hugo Tests",
+    journal   = "Hugo Websites",
+    year      = "2022",
+}