Merge pull request #11 from h200101/UTF-8 - thanks @h200101!

Added UTF-8 support

Author: eljojo

go.mod

@@ -19,4 +19,5 @@ require (
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
 	golang.org/x/crypto v0.46.0 // indirect
 	golang.org/x/sys v0.39.0 // indirect
+	golang.org/x/text v0.33.0 // indirect
 )

go.sum

@@ -24,6 +24,8 @@ golang.org/x/crypto v0.46.0 h1:cKRW/pmt1pKAfetfu+RCEvjvZkA9RimPbh7bhFjGVBU=
 golang.org/x/crypto v0.46.0/go.mod h1:Evb/oLKmMraqjZ2iQTwDwvCtJkczlDuTmdJXoZVzqU0=
 golang.org/x/sys v0.39.0 h1:CvCKL8MeisomCi6qNZ+wbb0DN9E5AATixKsvNtMoMFk=
 golang.org/x/sys v0.39.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
+golang.org/x/text v0.33.0 h1:B3njUFyqtHDUI5jMn1YIr5B0IE2U0qck04r6d4KPAxE=
+golang.org/x/text v0.33.0/go.mod h1:LuMebE6+rBincTi9+xWTY8TztLzKHc/9C1uBCG27+q8=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=

internal/bundle/bundle.go

@@ -9,6 +9,9 @@ import (
 	"regexp"
 	"strings"
 	"time"
+	"unicode"
+
+	"golang.org/x/text/unicode/norm"
 
 	"github.com/eljojo/rememory/internal/core"
 	"github.com/eljojo/rememory/internal/html"
@@ -213,10 +216,21 @@ func loadShares(p *project.Project) ([]*core.Share, error) {
 	return shares, nil
 }
 
-// sanitizeName converts a name to a filesystem-safe lowercase string.
+// sanitizeName converts a name to a filesystem-safe lowercase ASCII string.
+// It transliterates accented/diacritic characters to their ASCII base form
+// (e.g. "José" → "jose", "Ñoño" → "nono") so that filenames are always valid.
 func sanitizeName(name string) string {
+	// Decompose to NFD: splits characters like "é" into "e" + combining accent.
+	// Then drop combining marks to keep only the base letter.
+	var stripped []rune
+	for _, r := range norm.NFD.String(name) {
+		if !unicode.Is(unicode.Mn, r) { // Mn = Mark, Nonspacing (combining diacritics)
+			stripped = append(stripped, r)
+		}
+	}
+
 	result := ""
-	for _, r := range name {
+	for _, r := range stripped {
 		if (r >= 'a' && r <= 'z') || (r >= 'A' && r <= 'Z') || (r >= '0' && r <= '9') {
 			result += string(r)
 		} else if r == ' ' || r == '-' || r == '_' {

internal/pdf/fonts.go

@@ -0,0 +1,47 @@
+package pdf
+
+import (
+	_ "embed"
+
+	"github.com/go-pdf/fpdf"
+)
+
+// DejaVu Sans font files (Bitstream Vera / DejaVu license - see fonts/LICENSE-DejaVu.txt)
+// These provide comprehensive UTF-8 / Unicode coverage including Latin, Cyrillic,
+// Greek, Arabic, Hebrew, and many other scripts.
+
+//go:embed fonts/DejaVuSans.ttf
+var dejaVuSansRegular []byte
+
+//go:embed fonts/DejaVuSans-Bold.ttf
+var dejaVuSansBold []byte
+
+//go:embed fonts/DejaVuSans-Oblique.ttf
+var dejaVuSansOblique []byte
+
+//go:embed fonts/DejaVuSans-BoldOblique.ttf
+var dejaVuSansBoldOblique []byte
+
+//go:embed fonts/DejaVuSansMono.ttf
+var dejaVuSansMonoRegular []byte
+
+//go:embed fonts/DejaVuSansMono-Bold.ttf
+var dejaVuSansMonoBold []byte
+
+// Font family names used throughout the PDF generator.
+const (
+	fontSans = "DejaVuSans"
+	fontMono = "DejaVuSansMono"
+)
+
+// registerUTF8Fonts adds the embedded DejaVu Sans UTF-8 fonts to the PDF instance.
+// After calling this, use fontSans and fontMono as the family name in SetFont().
+func registerUTF8Fonts(pdf *fpdf.Fpdf) {
+	pdf.AddUTF8FontFromBytes(fontSans, "", dejaVuSansRegular)
+	pdf.AddUTF8FontFromBytes(fontSans, "B", dejaVuSansBold)
+	pdf.AddUTF8FontFromBytes(fontSans, "I", dejaVuSansOblique)
+	pdf.AddUTF8FontFromBytes(fontSans, "BI", dejaVuSansBoldOblique)
+
+	pdf.AddUTF8FontFromBytes(fontMono, "", dejaVuSansMonoRegular)
+	pdf.AddUTF8FontFromBytes(fontMono, "B", dejaVuSansMonoBold)
+}