processing/text: Add LineToParagraph processor for HTML paragraph conversion

processing/text/processor.go

@@ -1,7 +1,9 @@
 package text
 
 import (
+	"bufio"
 	"fmt"
+	"html"
 	"regexp"
 	"strings"
 )
@@ -24,6 +26,7 @@ var (
 	_ Processor = RegexpRemover{}
 	_ Processor = Cutter{}
 	_ Processor = Trimmer{}
+	_ Processor = LineToParagraph{}
 )
 
 // processor is a generic implementation of Processor,
@@ -137,6 +140,51 @@ func (p Trimmer) Process(s string) (string, error) {
 	return strings.Trim(s, p.Cutset), nil
 }
 
+// LineToParagraph converts each line of text into a separate HTML <p>...</p> paragraph.
+// TrimSpace controls whether leading and trailing spaces are removed from each line before wrapping it in <p> tags.
+// Empty lines can be either skipped or rendered as empty <p></p> according to the SkipEmpty flag.
+type LineToParagraph struct {
+	// TrimSpace controls whether leading and trailing spaces are removed from each line.
+	// true  → trim spaces
+	// false → preserve spaces (default, matches previous behaviour)
+	TrimSpace bool
+	// SkipEmpty controls whether completely empty lines produce <p></p> or are ignored.
+	// true  → skip empty lines (default, matches previous behaviour)
+	// false → emit <p></p> for empty lines
+	SkipEmpty bool
+}
+
+// Describe returns a human-readable description of the processor.
+func (p LineToParagraph) Describe() string {
+	return fmt.Sprintf("LineToParagraph(TrimSpace=%t, SkipEmpty=%t)", p.TrimSpace, p.SkipEmpty)
+}
+
+// Once returns true – the transformation is idempotent and should run only once.
+func (LineToParagraph) Once() bool { return true }
+
+// Process transforms the input text line-by-line into HTML paragraphs.
+func (p LineToParagraph) Process(s string) (string, error) {
+	scanner := bufio.NewScanner(strings.NewReader(s))
+	var b strings.Builder
+	b.Grow(len(s))
+	for scanner.Scan() {
+		line := scanner.Text()
+		if p.TrimSpace {
+			line = strings.TrimSpace(line)
+		}
+		if p.SkipEmpty && line == "" {
+			continue
+		}
+		b.WriteString("<p>")
+		b.WriteString(html.EscapeString(line))
+		b.WriteString("</p>\n")
+	}
+	if err := scanner.Err(); err != nil {
+		return "", err
+	}
+	return b.String(), nil
+}
+
 // TrimSpace returns a processor that removes leading and trailing spaces.
 func TrimSpace() Processor {
 	return NewProcessor("TrimSpace", false, WrapFunc(strings.TrimSpace))
@@ -162,6 +210,12 @@ func RemoveParentheses() Processor {
 	)
 }
 
+// ToParagraphs returns a processor that converts each line into a <p> paragraph.
+// If skipEmpty is true, empty lines are ignored; otherwise, they produce empty <p></p>.
+func ToParagraphs(skipEmpty bool) Processor {
+	return LineToParagraph{SkipEmpty: skipEmpty}
+}
+
 // WrapFunc wraps a simple string -> string function
 // into a function matching the Processor signature.
 func WrapFunc(fn func(string) string) func(string) (string, error) {

processing/text/processor_test.go

@@ -60,3 +60,74 @@ func TestTrimmer(t *testing.T) {
 		}
 	}
 }
+
+func TestLineToParagraph(t *testing.T) {
+	for i, tc := range []struct {
+		proc     Processor
+		input    string
+		expected string
+	}{
+		// Default behaviour (zero value): SkipEmpty=true, TrimSpace=false
+		{
+			LineToParagraph{},
+			"  First line  \n\n  Second line\t \n\n",
+			"<p>  First line  </p>\n<p></p>\n<p>  Second line\t </p>\n<p></p>\n",
+		},
+		// Explicitly enable trimming of leading/trailing whitespace
+		{
+			LineToParagraph{TrimSpace: true},
+			"  Hello   \n  World  \n",
+			"<p>Hello</p>\n<p>World</p>\n",
+		},
+		// Preserve empty lines (SkipEmpty = false)
+		{
+			LineToParagraph{SkipEmpty: false},
+			"Line 1\n\n\nLine 2\n",
+			"<p>Line 1</p>\n<p></p>\n<p></p>\n<p>Line 2</p>\n",
+		},
+		// Trim + preserve empty lines
+		{
+			LineToParagraph{TrimSpace: true, SkipEmpty: false},
+			"   \n  A  \n   \nB   \n",
+			"<p></p>\n<p>A</p>\n<p></p>\n<p>B</p>\n",
+		},
+		// Fully literal mode: keep all original whitespace and emit every line
+		{
+			LineToParagraph{TrimSpace: false, SkipEmpty: false},
+			"\tIndented\n  \n    Spaces only   \n\nTrailing \n",
+			"<p>\tIndented</p>\n<p>  </p>\n<p>    Spaces only   </p>\n<p></p>\n<p>Trailing </p>\n",
+		},
+		// Empty input
+		{
+			LineToParagraph{},
+			"",
+			"",
+		},
+		// Input containing only empty lines and whitespace
+		{
+			LineToParagraph{},
+			"\n   \n\t\n  \n",
+			"<p></p>\n<p>   </p>\n<p>\t</p>\n<p>  </p>\n",
+		},
+		// HTML escaping works regardless of configuration
+		{
+			LineToParagraph{TrimSpace: true},
+			" <script>alert(1)</script> \n &copy; 2025 \n",
+			"<p>&lt;script&gt;alert(1)&lt;/script&gt;</p>\n<p>&amp;copy; 2025</p>\n",
+		},
+		{
+			LineToParagraph{TrimSpace: false},
+			"  <b>bold</b>  \n",
+			"<p>  &lt;b&gt;bold&lt;/b&gt;  </p>\n",
+		},
+	} {
+		res, err := NewTasks().Append(tc.proc).Process(tc.input)
+		if err != nil {
+			t.Errorf("case %d: unexpected error: %v", i, err)
+			continue
+		}
+		if res != tc.expected {
+			t.Errorf("case %d:\ngot:\n%q\nwant:\n%q", i, res, tc.expected)
+		}
+	}
+}

processing/text/task.go

@@ -1,8 +1,6 @@
 package text
 
-import (
-	"fmt"
-)
+import "fmt"
 
 var MaxIter = 100