Merge: t-paliad-349 docforge slice 1 — extract .docx engine to pkg/docforge/docx (m/paliad#157)

internal/services/docforge_shims.go

@@ -0,0 +1,65 @@
+package services
+
+// Shims bridging the submission generator to the extracted docforge .docx
+// adapter (pkg/docforge/docx). Slice 1 of the docforge train
+// (t-paliad-349 / m/paliad#157) relocated the Markdown→OOXML walker, the
+// placeholder substitution engine, and the .dotm→.docx converter into
+// pkg/docforge/docx with no behaviour change. These type aliases and
+// forwarders keep every existing caller in internal/services and
+// internal/handlers compiling and behaving identically — the names,
+// signatures, and semantics are unchanged; only the implementation moved.
+//
+// Later slices retire these shims as the submission services are
+// refactored to call docforge directly through the neutral model and the
+// VariableResolver interface.
+
+import "mgit.msbls.de/m/paliad/pkg/docforge/docx"
+
+// PlaceholderMap is the variable bag (dotted-key → substituted value),
+// built by SubmissionVarsService and consumed by the renderer.
+type PlaceholderMap = docx.PlaceholderMap
+
+// MissingPlaceholderFn translates an unbound placeholder key into the
+// in-document marker token.
+type MissingPlaceholderFn = docx.MissingPlaceholderFn
+
+// SubmissionRenderer renders a .docx template by substituting
+// {{placeholder}} tokens. Stateless; safe for concurrent use.
+type SubmissionRenderer = docx.SubmissionRenderer
+
+// HyperlinkAllocator hands the Markdown walker a rId for each external
+// URL it encounters in [label](url) inline links.
+type HyperlinkAllocator = docx.HyperlinkAllocator
+
+// NewSubmissionRenderer constructs the renderer.
+func NewSubmissionRenderer() *SubmissionRenderer { return docx.NewSubmissionRenderer() }
+
+// DefaultMissingMarker returns the standard missing-value marker for the
+// given UI language ("[KEIN WERT: <key>]" / "[NO VALUE: <key>]").
+func DefaultMissingMarker(lang string) MissingPlaceholderFn { return docx.DefaultMissingMarker(lang) }
+
+// RenderMarkdownToOOXML renders Markdown source into OOXML paragraph
+// elements using a single paragraph style.
+func RenderMarkdownToOOXML(md, paragraphStyle string) string {
+	return docx.RenderMarkdownToOOXML(md, paragraphStyle)
+}
+
+// RenderMarkdownToOOXMLWithStyles is the full rich-prose entry point
+// (headings, lists, blockquote, inline hyperlinks via the allocator).
+func RenderMarkdownToOOXMLWithStyles(md string, stylemap map[string]string, links HyperlinkAllocator) string {
+	return docx.RenderMarkdownToOOXMLWithStyles(md, stylemap, links)
+}
+
+// ConvertDotmToDocx rewrites a .dotm/.docm/.dotx zip into a clean .docx
+// zip. Idempotent on a zip that is already a plain .docx.
+func ConvertDotmToDocx(dotmBytes []byte) ([]byte, error) { return docx.ConvertDotmToDocx(dotmBytes) }
+
+// SanitiseSubmissionFileName cleans a string for use inside a download
+// filename (strips path separators / quotes, ASCII-folds DE umlauts).
+func SanitiseSubmissionFileName(s string) string { return docx.SanitiseSubmissionFileName(s) }
+
+// xmlAttrEscape forwards to docx.XMLAttrEscape so submission_compose.go's
+// hyperlink-rels inserts reuse the walker's exact attribute escaping
+// without importing the docx package directly. Retires when the composer
+// splice folds into pkg/docforge/docx (slice 2).
+func xmlAttrEscape(s string) string { return docx.XMLAttrEscape(s) }

internal/services/submission_vars_pretty_test.go

@@ -0,0 +1,81 @@
+package services
+
+// Pretty-printer tests for the variable-resolution layer (legalSourcePretty,
+// ourSideDE/EN, patentNumberUPC). These live with submission_vars.go;
+// they were relocated out of the docx engine test suite when the
+// .docx renderer moved to pkg/docforge/docx (t-paliad-349 slice 1).
+
+import "testing"
+
+func TestLegalSourcePretty(t *testing.T) {
+	tests := []struct {
+		src, lang, want string
+	}{
+		{"DE.ZPO.276.1", "de", "§ 276 Abs. 1 ZPO"},
+		{"DE.ZPO.276.1", "en", "Section 276(1) ZPO"},
+		{"DE.ZPO.253", "de", "§ 253 ZPO"},
+		{"DE.ZPO.253", "en", "Section 253 ZPO"},
+		{"UPC.RoP.23.1", "de", "Regel 23.1 VerfO UPC"},
+		{"UPC.RoP.23.1", "en", "Rule 23.1 RoP UPC"},
+		{"UPC.RoP.198", "de", "Regel 198 VerfO UPC"},
+		{"DE.PatG.83", "de", "§ 83 PatG"},
+		{"EPC.123", "de", "Art. 123 EPÜ"},
+		{"EPC.123", "en", "Art. 123 EPC"},
+		{"FOO.BAR.123", "de", "FOO.BAR.123"},
+		{"", "de", ""},
+	}
+	for _, tc := range tests {
+		t.Run(tc.src+"/"+tc.lang, func(t *testing.T) {
+			got := legalSourcePretty(tc.src, tc.lang)
+			if got != tc.want {
+				t.Errorf("legalSourcePretty(%q, %q) = %q, want %q", tc.src, tc.lang, got, tc.want)
+			}
+		})
+	}
+}
+
+func TestOurSideTranslations(t *testing.T) {
+	cases := []struct {
+		in, wantDE, wantEN string
+	}{
+		{"claimant", "Klägerin", "Claimant"},
+		{"defendant", "Beklagte", "Defendant"},
+		{"court", "Gericht", "Court"},
+		{"both", "Klägerin und Beklagte", "Claimant and Defendant"},
+		{"", "", ""},
+		{"unknown", "", ""},
+	}
+	for _, tc := range cases {
+		t.Run(tc.in, func(t *testing.T) {
+			if got := ourSideDE(tc.in); got != tc.wantDE {
+				t.Errorf("ourSideDE(%q) = %q, want %q", tc.in, got, tc.wantDE)
+			}
+			if got := ourSideEN(tc.in); got != tc.wantEN {
+				t.Errorf("ourSideEN(%q) = %q, want %q", tc.in, got, tc.wantEN)
+			}
+		})
+	}
+}
+
+func TestPatentNumberUPC(t *testing.T) {
+	tests := []struct {
+		in, want string
+	}{
+		{"EP 1 234 567 B1", "EP 1 234 567 (B1)"},
+		{"EP 4 056 049 A1", "EP 4 056 049 (A1)"},
+		{"DE 10 2020 123 456 A1", "DE 10 2020 123 456 (A1)"},
+		{"EP 1 234 567", "EP 1 234 567"},
+		{"  EP 1 234 567 B1  ", "EP 1 234 567 (B1)"},
+		{"", ""},
+		{"WO/2023/123456", "WO/2023/123456"},
+		{"EP 1 234 567 B12", "EP 1 234 567 B12"},
+	}
+	for _, tc := range tests {
+		t.Run(tc.in, func(t *testing.T) {
+			got := patentNumberUPC(tc.in)
+			if got != tc.want {
+				t.Errorf("patentNumberUPC(%q) = %q, want %q", tc.in, got, tc.want)
+			}
+		})
+	}
+}

pkg/docforge/doc.go

@@ -0,0 +1,24 @@
+// Package docforge is paliad's modular document-generator engine — the
+// format-neutral core that turns templates + variables into rendered
+// documents, with format-specific adapters living in sub-packages.
+//
+// The package is being extracted from the in-tree submission generator
+// (internal/services/submission_*.go) per the PRD in
+// docs/plans/prd-docforge-2026-05-29.md (t-paliad-349 / m/paliad#157).
+// The extraction follows the same packaging discipline as
+// pkg/litigationplanner: docforge owns its types and exposes interfaces
+// for the stateful inputs (variable resolution, template storage); the
+// consuming application (paliad) implements those interfaces against its
+// own database, and a future second consumer reaches the engine over an
+// HTTP veneer rather than importing it.
+//
+// Slice 1 (this commit) relocates the .docx adapter — the Markdown→OOXML
+// walker, the placeholder substitution engine, and the .dotm→.docx
+// converter — into pkg/docforge/docx with no behaviour change. paliad's
+// internal/services package keeps thin type-alias + forwarder shims so
+// the submission generator and its HTTP surface compile and behave
+// identically. Later slices introduce the neutral document model,
+// hoist the format-neutral placeholder grammar up to this root package,
+// and add the VariableResolver interface, the TemplateStore, the
+// authoring surface, and the pluggable Exporter.
+package docforge

pkg/docforge/docx/doc.go

@@ -0,0 +1,28 @@
+// Package docx is docforge's .docx (OOXML) adapter — the first
+// format adapter in the docforge engine (t-paliad-349 / m/paliad#157).
+//
+// It owns the in-house OOXML machinery extracted from paliad's submission
+// generator in slice 1, with no behaviour change:
+//
+//   - merge.go    — the placeholder substitution renderer
+//     (SubmissionRenderer.Render / RenderHTML). Two-pass {{placeholder}}
+//     substitution (single-run, then cross-run merge for fragmented
+//     placeholders), plus the preview-HTML emitter that wraps substituted
+//     values in clickable <span class="draft-var" data-var="…"> markup.
+//   - markdown.go — the Markdown→OOXML walker (RenderMarkdownToOOXML*),
+//     including the b78a984 fix that preserves {{…}} placeholders verbatim
+//     through inline-span parsing (underscores in keys survive).
+//   - dotm.go     — ConvertDotmToDocx: strips macros from a .dotm/.docm/
+//     .dotx and rewrites the content-types + rels to a clean .docx,
+//     passing every other part through bit-for-bit.
+//
+// Why no third-party docx library: lukasjarosch/go-docx treats sibling
+// placeholders in one run ("{{a}} ./. {{b}}") as nested and refuses to
+// replace either; patent submissions routinely have several placeholders
+// per paragraph, so this in-house renderer is required. See merge.go.
+//
+// The placeholder grammar — \{\{\s*([A-Za-z][A-Za-z0-9_.]*)\s*\}\} — and
+// the PlaceholderMap type currently live here with the renderer; a later
+// slice hoists the format-neutral grammar up to the docforge root once
+// the neutral document model and the VariableResolver interface land.
+package docx

pkg/docforge/docx/dotm.go

@@ -1,4 +1,4 @@
-package services
+package docx
 
 // Submission .dotm → .docx converter (t-paliad-230, "format-only" scope
 // reduction of the original t-paliad-215 submission generator).

pkg/docforge/docx/dotm_test.go

@@ -1,4 +1,4 @@
-package services
+package docx
 
 import (
 	"archive/zip"

pkg/docforge/docx/markdown.go

@@ -1,4 +1,4 @@
-package services
+package docx
 
 // Markdown → OOXML walker for Composer section content (t-paliad-313
 // Slice B, design doc §9.2).
@@ -492,6 +492,14 @@ func xmlTextEscape(s string) string {
 	return s
 }
 
+// XMLAttrEscape is the exported form of xmlAttrEscape, used by the
+// paliad-side composer (submission_compose.go) when it builds hyperlink
+// relationship inserts. It exists so the composer can reuse the exact
+// attribute-escaping the walker applies without reaching across the
+// package boundary for an unexported helper. Slice 2 folds the
+// composer's splice into this package, after which the wrapper retires.
+func XMLAttrEscape(s string) string { return xmlAttrEscape(s) }
+
 // xmlAttrEscape escapes for safe insertion into an attribute value
 // (e.g. `<w:pStyle w:val="…"/>`).
 func xmlAttrEscape(s string) string {

pkg/docforge/docx/markdown_test.go

@@ -1,4 +1,4 @@
-package services
+package docx
 
 // Unit tests for the Composer's Markdown → OOXML walker (t-paliad-313
 // Slice B). Pure function; no DB dependency.

pkg/docforge/docx/merge.go

@@ -1,4 +1,4 @@
-package services
+package docx
 
 // Submission template renderer — in-house engine for the submission
 // draft editor (t-paliad-238, design doc

pkg/docforge/docx/merge_test.go

@@ -1,4 +1,4 @@
-package services
+package docx
 
 // Submission merge-engine tests — resurrected from the original
 // t-paliad-215 Slice 1 (commit 8ea3509) + Slice 2 (commit 1765d5e).
@@ -190,79 +190,6 @@ func TestPlaceholderRegex_Boundaries(t *testing.T) {
 	}
 }
 
-func TestLegalSourcePretty(t *testing.T) {
-	tests := []struct {
-		src, lang, want string
-	}{
-		{"DE.ZPO.276.1", "de", "§ 276 Abs. 1 ZPO"},
-		{"DE.ZPO.276.1", "en", "Section 276(1) ZPO"},
-		{"DE.ZPO.253", "de", "§ 253 ZPO"},
-		{"DE.ZPO.253", "en", "Section 253 ZPO"},
-		{"UPC.RoP.23.1", "de", "Regel 23.1 VerfO UPC"},
-		{"UPC.RoP.23.1", "en", "Rule 23.1 RoP UPC"},
-		{"UPC.RoP.198", "de", "Regel 198 VerfO UPC"},
-		{"DE.PatG.83", "de", "§ 83 PatG"},
-		{"EPC.123", "de", "Art. 123 EPÜ"},
-		{"EPC.123", "en", "Art. 123 EPC"},
-		{"FOO.BAR.123", "de", "FOO.BAR.123"},
-		{"", "de", ""},
-	}
-	for _, tc := range tests {
-		t.Run(tc.src+"/"+tc.lang, func(t *testing.T) {
-			got := legalSourcePretty(tc.src, tc.lang)
-			if got != tc.want {
-				t.Errorf("legalSourcePretty(%q, %q) = %q, want %q", tc.src, tc.lang, got, tc.want)
-			}
-		})
-	}
-}
-
-func TestOurSideTranslations(t *testing.T) {
-	cases := []struct {
-		in, wantDE, wantEN string
-	}{
-		{"claimant", "Klägerin", "Claimant"},
-		{"defendant", "Beklagte", "Defendant"},
-		{"court", "Gericht", "Court"},
-		{"both", "Klägerin und Beklagte", "Claimant and Defendant"},
-		{"", "", ""},
-		{"unknown", "", ""},
-	}
-	for _, tc := range cases {
-		t.Run(tc.in, func(t *testing.T) {
-			if got := ourSideDE(tc.in); got != tc.wantDE {
-				t.Errorf("ourSideDE(%q) = %q, want %q", tc.in, got, tc.wantDE)
-			}
-			if got := ourSideEN(tc.in); got != tc.wantEN {
-				t.Errorf("ourSideEN(%q) = %q, want %q", tc.in, got, tc.wantEN)
-			}
-		})
-	}
-}
-
-func TestPatentNumberUPC(t *testing.T) {
-	tests := []struct {
-		in, want string
-	}{
-		{"EP 1 234 567 B1", "EP 1 234 567 (B1)"},
-		{"EP 4 056 049 A1", "EP 4 056 049 (A1)"},
-		{"DE 10 2020 123 456 A1", "DE 10 2020 123 456 (A1)"},
-		{"EP 1 234 567", "EP 1 234 567"},
-		{"  EP 1 234 567 B1  ", "EP 1 234 567 (B1)"},
-		{"", ""},
-		{"WO/2023/123456", "WO/2023/123456"},
-		{"EP 1 234 567 B12", "EP 1 234 567 B12"},
-	}
-	for _, tc := range tests {
-		t.Run(tc.in, func(t *testing.T) {
-			got := patentNumberUPC(tc.in)
-			if got != tc.want {
-				t.Errorf("patentNumberUPC(%q) = %q, want %q", tc.in, got, tc.want)
-			}
-		})
-	}
-}
-
 // TestRenderHTML_ExtractsParagraphsAndFormatting verifies the preview
 // HTML emitter walks <w:p> / <w:r> / <w:t> correctly and carries
 // bold/italic through to <strong>/<em>. Substituted placeholders are