markup: add --citeproc to pandoc converter

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

@@ -0,0 +1,50 @@
+---
+title: Bibliographies in Markdown
+linkTitle: Bibliography
+description: Include citations and a bibliography in Markdown using LaTeX markup.
+categories: [content management]
+keywords: [latex,pandoc,citation,reference,bibliography]
+menu:
+  docs:
+    parent: content-management
+    weight: 320
+weight: 320
+toc: true
+---
+
+{{< new-in 0.144.0 />}}
+
+## Citations and Bibliographies
+
+[Pandoc](https://pandoc.org) is a universal document converter and can be used to convert markdown files.
+
+With **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-specific 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.

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

@@ -111,6 +111,12 @@ Hugo passes these CLI flags when calling the Pandoc executable:
 --mathjax
 ```
 
+If your Pandoc has version 2.11 or later, it also passes this CLI flag:
+
+```text
+--citeproc
+```
+
 [Pandoc]: https://pandoc.org/
 
 ### reStructuredText

markup/pandoc/convert.go

@@ -15,10 +15,12 @@
 package pandoc
 
 import (
+	"bytes"
+	"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"
 )
@@ -64,6 +66,9 @@ 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)
 }
 
@@ -76,6 +81,45 @@ func getPandocBinaryName() string {
 	return ""
 }
 
+var pandocSupportsCiteprocOnce sync.Once
+var pandocSupportsCiteproc bool
+
+// getPandocSupportsCiteproc runs a dump-args to determine if pandoc knows the --citeproc argument
+func getPandocSupportsCiteproc(cfg converter.ProviderConfig) (bool, error) {
+	var err error
+
+	pandocSupportsCiteprocOnce.Do(func() {
+		argsv := []any{"--dump-args", "--citeproc"}
+
+		var out bytes.Buffer
+		argsv = append(argsv, hexec.WithStdout(&out))
+
+		cmd, err := cfg.Exec.New(pandocBinary, argsv...)
+		if err != nil {
+			pandocSupportsCiteproc = false
+			return
+		}
+
+		err = cmd.Run()
+		if err != nil {
+			pandocSupportsCiteproc = false
+			return
+		}
+		pandocSupportsCiteproc = true
+	})
+
+	return pandocSupportsCiteproc, err
+}
+
+// supportsCitations returns true if citeproc is available
+func supportsCitations(cfg converter.ProviderConfig) bool {
+	if Supports() {
+		supportsCiteproc, err := getPandocSupportsCiteproc(cfg)
+		return supportsCiteproc && err == nil
+	}
+	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")
 	}
@@ -34,11 +34,109 @@ func TestConvert(t *testing.T) {
 	var err error
 	sc.Exec.Allow, err = security.NewWhitelist("pandoc")
 	c.Assert(err, qt.IsNil)
-	p, err := Provider.New(converter.ProviderConfig{Exec: hexec.New(sc, "", loggers.NewDefault()), Logger: loggers.NewDefault()})
+	cfg := converter.ProviderConfig{Exec: hexec.New(sc, "", loggers.NewDefault()), Logger: loggers.NewDefault()}
+	p, err := Provider.New(cfg)
 	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, expectContained []string, expectNotContained []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")
+	for _, expected := range expectContained {
+		c.Assert(string(output.Bytes()), qt.Contains, expected)
+	}
+	for _, notExpected := range expectNotContained {
+		c.Assert(string(output.Bytes()), qt.Not(qt.Contains), notExpected)
+	}
+}
+
+func TestGetPandocSupportsCiteprocCallTwice(t *testing.T) {
+	c, _, cfg := setupTestConverter(t)
+
+	supports1, err1 := getPandocSupportsCiteproc(cfg)
+	supports2, err2 := getPandocSupportsCiteproc(cfg)
+	c.Assert(supports1, qt.Equals, supports2)
+	c.Assert(err1, qt.IsNil)
+	c.Assert(err2, qt.IsNil)
+}
+
+func TestCiteprocWithHugoMeta(t *testing.T) {
+	content := `
+---
+title: Test
+published: 2022-05-30
+---
+testContent
+`
+	expected := []string{"testContent"}
+	unexpected := []string{"Doe", "Mustermann", "2022", "Treatise"}
+	runCiteprocTest(t, content, expected, unexpected)
+}
+
+func TestCiteprocWithPandocMeta(t *testing.T) {
+	content := `
+---
+---
+---
+...
+testContent
+`
+	expected := []string{"testContent"}
+	unexpected := []string{"Doe", "Mustermann", "2022", "Treatise"}
+	runCiteprocTest(t, content, expected, unexpected)
+}
+
+func TestCiteprocWithBibliography(t *testing.T) {
+	content := `
+---
+---
+---
+bibliography: testdata/bibliography.bib
+...
+testContent
+`
+	expected := []string{"testContent"}
+	unexpected := []string{"Doe", "Mustermann", "2022", "Treatise"}
+	runCiteprocTest(t, content, expected, unexpected)
+}
+
+func TestCiteprocWithExplicitCitation(t *testing.T) {
+	content := `
+---
+---
+---
+bibliography: testdata/bibliography.bib
+...
+@Doe2022
+`
+	expected := []string{"Doe", "Mustermann", "2022", "Treatise"}
+	runCiteprocTest(t, content, expected, []string{})
+}
+
+func TestCiteprocWithNocite(t *testing.T) {
+	content := `
+---
+---
+---
+bibliography: testdata/bibliography.bib
+nocite: |
+  @*
+...
+`
+	expected := []string{"Doe", "Mustermann", "2022", "Treatise"}
+	runCiteprocTest(t, content, expected, []string{})
 }

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",
+}