// parseCollation parses XML files in the collation directory of the CLDR core.zip file.
func parseCollation(b *build.Builder) {
d := &cldr.Decoder{}
d.SetDirFilter("collation")
data := decodeCLDR(d)
for _, loc := range data.Locales() {
x, err := data.LDML(loc)
failOnError(err)
if skipLang(x.Identity.Language.Type) {
continue
}
cs := x.Collations.Collation
sl := cldr.MakeSlice(&cs)
if !types.all {
sl.SelectAnyOf("type", append(types.s, x.Collations.Default())...)
}
sl.SelectOnePerGroup("alt", altInclude())
for _, c := range cs {
m := make(map[locale.Part]string)
m[locale.TagPart] = loc
if c.Type != x.Collations.Default() {
m[locale.Extension('u')] = "co-" + c.Type
}
id, err := locale.Compose(m)
failOnError(err)
t := b.Tailoring(id)
c.Process(processor{t})
}
}
}
// parseUCA parses a Default Unicode Collation Element Table of the format
// specified in http://www.unicode.org/reports/tr10/#File_Format.
// It returns the variable top.
func parseUCA(builder *build.Builder) {
r := openReader(*ducet)
defer r.Close()
input := bufio.NewReader(r)
colelem := regexp.MustCompile(`\[([.*])([0-9A-F.]+)\]`)
for i := 1; true; i++ {
l, prefix, err := input.ReadLine()
if err == io.EOF {
break
}
Error(err)
line := string(l)
if prefix {
log.Fatalf("%d: buffer overflow", i)
}
if len(line) == 0 || line[0] == '#' {
continue
}
if line[0] == '@' {
if strings.HasPrefix(line[1:], "version ") {
if v := strings.Split(line[1:], " ")[1]; v != unicode.Version {
log.Fatalf("incompatible version %s; want %s", v, unicode.Version)
}
}
} else {
// parse entries
part := strings.Split(line, " ; ")
if len(part) != 2 {
log.Fatalf("%d: production rule without ';': %v", i, line)
}
lhs := []rune{}
for _, v := range strings.Split(part[0], " ") {
if v != "" {
lhs = append(lhs, rune(convHex(i, v)))
}
}
vars := []int{}
rhs := [][]int{}
for i, m := range colelem.FindAllStringSubmatch(part[1], -1) {
if m[1] == "*" {
vars = append(vars, i)
}
elem := []int{}
for _, h := range strings.Split(m[2], ".") {
elem = append(elem, convHex(i, h))
}
rhs = append(rhs, elem)
}
builder.Add(lhs, rhs, vars)
}
}
}
// parseUCA parses a Default Unicode Collation Element Table of the format
// specified in http://www.unicode.org/reports/tr10/#File_Format.
// It returns the variable top.
func parseUCA(builder *build.Builder) {
var r io.ReadCloser
var err error
if strings.HasSuffix(*root, ".zip") {
for _, f := range openArchive(root).File {
if strings.HasSuffix(f.Name, "allkeys_CLDR.txt") {
r, err = f.Open()
}
}
if r == nil {
err = fmt.Errorf("file allkeys_CLDR.txt not found in archive %q", *root)
}
} else {
r, err = openReader(root)
}
failOnError(err)
defer r.Close()
scanner := bufio.NewScanner(r)
colelem := regexp.MustCompile(`\[([.*])([0-9A-F.]+)\]`)
for i := 1; scanner.Scan(); i++ {
line := scanner.Text()
if len(line) == 0 || line[0] == '#' {
continue
}
if line[0] == '@' {
// parse properties
switch {
case strings.HasPrefix(line[1:], "version "):
a := strings.Split(line[1:], " ")
if a[1] != unicode.Version {
log.Fatalf("incompatible version %s; want %s", a[1], unicode.Version)
}
case strings.HasPrefix(line[1:], "backwards "):
log.Fatalf("%d: unsupported option backwards", i)
default:
log.Printf("%d: unknown option %s", i, line[1:])
}
} else {
// parse entries
part := strings.Split(line, " ; ")
if len(part) != 2 {
log.Fatalf("%d: production rule without ';': %v", i, line)
}
lhs := []rune{}
for _, v := range strings.Split(part[0], " ") {
if v == "" {
continue
}
lhs = append(lhs, rune(convHex(i, v)))
}
var n int
var vars []int
rhs := [][]int{}
for i, m := range colelem.FindAllStringSubmatch(part[1], -1) {
n += len(m[0])
elem := []int{}
for _, h := range strings.Split(m[2], ".") {
elem = append(elem, convHex(i, h))
}
if m[1] == "*" {
vars = append(vars, i)
}
rhs = append(rhs, elem)
}
if len(part[1]) < n+3 || part[1][n+1] != '#' {
log.Fatalf("%d: expected comment; found %s", i, part[1][n:])
}
if *test {
testInput.add(string(lhs))
}
failOnError(builder.Add(lhs, rhs, vars))
}
}
if scanner.Err() != nil {
log.Fatal(scanner.Err())
}
}