Commit b50a847c authored by Russ Cox's avatar Russ Cox

csv, gob, json, mail, mime, xml: use rune

Nothing terribly interesting here.

R=golang-dev, r, borman
CC=golang-dev
https://golang.org/cl/5315043
parent 9f6d036f
......@@ -101,8 +101,8 @@ var (
//
// If TrimLeadingSpace is true, leading white space in a field is ignored.
type Reader struct {
Comma int // Field delimiter (set to ',' by NewReader)
Comment int // Comment character for start of line
Comma rune // Field delimiter (set to ',' by NewReader)
Comment rune // Comment character for start of line
FieldsPerRecord int // Number of expected fields per record
LazyQuotes bool // Allow lazy quotes
TrailingComma bool // Allow trailing comma
......@@ -173,23 +173,23 @@ func (r *Reader) ReadAll() (records [][]string, err os.Error) {
// readRune reads one rune from r, folding \r\n to \n and keeping track
// of how far into the line we have read. r.column will point to the start
// of this rune, not the end of this rune.
func (r *Reader) readRune() (int, os.Error) {
rune, _, err := r.r.ReadRune()
func (r *Reader) readRune() (rune, os.Error) {
r1, _, err := r.r.ReadRune()
// Handle \r\n here. We make the simplifying assumption that
// anytime \r is followed by \n that it can be folded to \n.
// We will not detect files which contain both \r\n and bare \n.
if rune == '\r' {
rune, _, err = r.r.ReadRune()
if r1 == '\r' {
r1, _, err = r.r.ReadRune()
if err == nil {
if rune != '\n' {
if r1 != '\n' {
r.r.UnreadRune()
rune = '\r'
r1 = '\r'
}
}
}
r.column++
return rune, err
return r1, err
}
// unreadRune puts the last rune read from r back.
......@@ -199,13 +199,13 @@ func (r *Reader) unreadRune() {
}
// skip reads runes up to and including the rune delim or until error.
func (r *Reader) skip(delim int) os.Error {
func (r *Reader) skip(delim rune) os.Error {
for {
rune, err := r.readRune()
r1, err := r.readRune()
if err != nil {
return err
}
if rune == delim {
if r1 == delim {
return nil
}
}
......@@ -224,12 +224,12 @@ func (r *Reader) parseRecord() (fields []string, err os.Error) {
// If we are support comments and it is the comment character
// then skip to the end of line.
rune, _, err := r.r.ReadRune()
r1, _, err := r.r.ReadRune()
if err != nil {
return nil, err
}
if r.Comment != 0 && rune == r.Comment {
if r.Comment != 0 && r1 == r.Comment {
return nil, r.skip('\n')
}
r.r.UnreadRune()
......@@ -252,10 +252,10 @@ func (r *Reader) parseRecord() (fields []string, err os.Error) {
// parseField parses the next field in the record. The read field is
// located in r.field. Delim is the first character not part of the field
// (r.Comma or '\n').
func (r *Reader) parseField() (haveField bool, delim int, err os.Error) {
func (r *Reader) parseField() (haveField bool, delim rune, err os.Error) {
r.field.Reset()
rune, err := r.readRune()
r1, err := r.readRune()
if err != nil {
// If we have EOF and are not at the start of a line
// then we return the empty field. We have already
......@@ -267,30 +267,30 @@ func (r *Reader) parseField() (haveField bool, delim int, err os.Error) {
}
if r.TrimLeadingSpace {
for rune != '\n' && unicode.IsSpace(rune) {
rune, err = r.readRune()
for r1 != '\n' && unicode.IsSpace(r1) {
r1, err = r.readRune()
if err != nil {
return false, 0, err
}
}
}
switch rune {
switch r1 {
case r.Comma:
// will check below
case '\n':
// We are a trailing empty field or a blank line
if r.column == 0 {
return false, rune, nil
return false, r1, nil
}
return true, rune, nil
return true, r1, nil
case '"':
// quoted field
Quoted:
for {
rune, err = r.readRune()
r1, err = r.readRune()
if err != nil {
if err == os.EOF {
if r.LazyQuotes {
......@@ -300,16 +300,16 @@ func (r *Reader) parseField() (haveField bool, delim int, err os.Error) {
}
return false, 0, err
}
switch rune {
switch r1 {
case '"':
rune, err = r.readRune()
if err != nil || rune == r.Comma {
r1, err = r.readRune()
if err != nil || r1 == r.Comma {
break Quoted
}
if rune == '\n' {
return true, rune, nil
if r1 == '\n' {
return true, r1, nil
}
if rune != '"' {
if r1 != '"' {
if !r.LazyQuotes {
r.column--
return false, 0, r.error(ErrQuote)
......@@ -321,21 +321,21 @@ func (r *Reader) parseField() (haveField bool, delim int, err os.Error) {
r.line++
r.column = -1
}
r.field.WriteRune(rune)
r.field.WriteRune(r1)
}
default:
// unquoted field
for {
r.field.WriteRune(rune)
rune, err = r.readRune()
if err != nil || rune == r.Comma {
r.field.WriteRune(r1)
r1, err = r.readRune()
if err != nil || r1 == r.Comma {
break
}
if rune == '\n' {
return true, rune, nil
if r1 == '\n' {
return true, r1, nil
}
if !r.LazyQuotes && rune == '"' {
if !r.LazyQuotes && r1 == '"' {
return false, 0, r.error(ErrBareQuote)
}
}
......@@ -353,20 +353,20 @@ func (r *Reader) parseField() (haveField bool, delim int, err os.Error) {
// are at the end of the line (being mindful
// of trimming spaces).
c := r.column
rune, err = r.readRune()
r1, err = r.readRune()
if r.TrimLeadingSpace {
for rune != '\n' && unicode.IsSpace(rune) {
rune, err = r.readRune()
for r1 != '\n' && unicode.IsSpace(r1) {
r1, err = r.readRune()
if err != nil {
break
}
}
}
if err == os.EOF || rune == '\n' {
if err == os.EOF || r1 == '\n' {
r.column = c // report the comma
return false, 0, r.error(ErrTrailingComma)
}
r.unreadRune()
}
return true, rune, nil
return true, r1, nil
}
......@@ -17,8 +17,8 @@ var readTests = []struct {
UseFieldsPerRecord bool // false (default) means FieldsPerRecord is -1
// These fields are copied into the Reader
Comma int
Comment int
Comma rune
Comment rune
FieldsPerRecord int
LazyQuotes bool
TrailingComma bool
......
......@@ -23,7 +23,7 @@ import (
//
// If UseCRLF is true, the Writer ends each record with \r\n instead of \n.
type Writer struct {
Comma int // Field delimiter (set to to ',' by NewWriter)
Comma rune // Field delimiter (set to to ',' by NewWriter)
UseCRLF bool // True to use \r\n as the line terminator
w *bufio.Writer
}
......@@ -58,8 +58,8 @@ func (w *Writer) Write(record []string) (err os.Error) {
return
}
for _, rune := range field {
switch rune {
for _, r1 := range field {
switch r1 {
case '"':
_, err = w.w.WriteString(`""`)
case '\r':
......@@ -73,7 +73,7 @@ func (w *Writer) Write(record []string) (err os.Error) {
err = w.w.WriteByte('\n')
}
default:
_, err = w.w.WriteRune(rune)
_, err = w.w.WriteRune(r1)
}
if err != nil {
return
......@@ -117,6 +117,6 @@ func (w *Writer) fieldNeedsQuotes(field string) bool {
return true
}
rune, _ := utf8.DecodeRuneInString(field)
return unicode.IsSpace(rune)
r1, _ := utf8.DecodeRuneInString(field)
return unicode.IsSpace(r1)
}
......@@ -606,14 +606,14 @@ func TestSliceReusesMemory(t *testing.T) {
}
// general slice
{
x := []int("abcd")
x := []rune("abcd")
enc := NewEncoder(buf)
err := enc.Encode(x)
if err != nil {
t.Errorf("ints: encode: %s", err)
}
// Decode into y, which is big enough.
y := []int("ABCDE")
y := []rune("ABCDE")
addr := &y[0]
dec := NewDecoder(buf)
err = dec.Decode(&y)
......
......@@ -805,15 +805,15 @@ func (d *decodeState) literalInterface() interface{} {
// getu4 decodes \uXXXX from the beginning of s, returning the hex value,
// or it returns -1.
func getu4(s []byte) int {
func getu4(s []byte) rune {
if len(s) < 6 || s[0] != '\\' || s[1] != 'u' {
return -1
}
rune, err := strconv.Btoui64(string(s[2:6]), 16)
r, err := strconv.Btoui64(string(s[2:6]), 16)
if err != nil {
return -1
}
return int(rune)
return rune(r)
}
// unquote converts a quoted JSON string literal s into an actual string t.
......@@ -843,8 +843,8 @@ func unquoteBytes(s []byte) (t []byte, ok bool) {
r++
continue
}
rune, size := utf8.DecodeRune(s[r:])
if rune == utf8.RuneError && size == 1 {
rr, size := utf8.DecodeRune(s[r:])
if rr == utf8.RuneError && size == 1 {
break
}
r += size
......@@ -899,23 +899,23 @@ func unquoteBytes(s []byte) (t []byte, ok bool) {
w++
case 'u':
r--
rune := getu4(s[r:])
if rune < 0 {
rr := getu4(s[r:])
if rr < 0 {
return
}
r += 6
if utf16.IsSurrogate(rune) {
rune1 := getu4(s[r:])
if dec := utf16.DecodeRune(rune, rune1); dec != unicode.ReplacementChar {
if utf16.IsSurrogate(rr) {
rr1 := getu4(s[r:])
if dec := utf16.DecodeRune(rr, rr1); dec != unicode.ReplacementChar {
// A valid pair; consume.
r += 6
w += utf8.EncodeRune(b[w:], dec)
break
}
// Invalid surrogate; fall back to replacement rune.
rune = unicode.ReplacementChar
rr = unicode.ReplacementChar
}
w += utf8.EncodeRune(b[w:], rune)
w += utf8.EncodeRune(b[w:], rr)
}
// Quote, control characters are invalid.
......@@ -930,9 +930,9 @@ func unquoteBytes(s []byte) (t []byte, ok bool) {
// Coerce to well-formed UTF-8.
default:
rune, size := utf8.DecodeRune(s[r:])
rr, size := utf8.DecodeRune(s[r:])
r += size
w += utf8.EncodeRune(b[w:], rune)
w += utf8.EncodeRune(b[w:], rr)
}
}
return b[0:w], true
......
......@@ -243,7 +243,7 @@ func TestHTMLEscape(t *testing.T) {
}
}
func noSpace(c int) int {
func noSpace(c rune) rune {
if isSpace(c) {
return -1
}
......
......@@ -176,7 +176,7 @@ func (s *scanner) popParseState() {
}
}
func isSpace(c int) bool {
func isSpace(c rune) bool {
return c == ' ' || c == '\t' || c == '\r' || c == '\n'
}
......
......@@ -261,13 +261,13 @@ func genValue(n int) interface{} {
func genString(stddev float64) string {
n := int(math.Abs(rand.NormFloat64()*stddev + stddev/2))
c := make([]int, n)
c := make([]rune, n)
for i := range c {
f := math.Abs(rand.NormFloat64()*64 + 32)
if f > 0x10ffff {
f = 0x10ffff
}
c[i] = int(f)
c[i] = rune(f)
}
return string(c)
}
......
......@@ -115,7 +115,7 @@ Input:
func nonSpace(b []byte) bool {
for _, c := range b {
if !isSpace(int(c)) {
if !isSpace(rune(c)) {
return true
}
}
......
......@@ -454,7 +454,7 @@ func decodeRFC2047Word(s string) (string, os.Error) {
case "iso-8859-1":
b := new(bytes.Buffer)
for _, c := range dec {
b.WriteRune(int(c))
b.WriteRune(rune(c))
}
return b.String(), nil
case "utf-8":
......
......@@ -10,16 +10,16 @@ import (
// isTSpecial returns true if rune is in 'tspecials' as defined by RFC
// 1521 and RFC 2045.
func isTSpecial(rune int) bool {
return strings.IndexRune(`()<>@,;:\"/[]?=`, rune) != -1
func isTSpecial(r rune) bool {
return strings.IndexRune(`()<>@,;:\"/[]?=`, r) != -1
}
// IsTokenChar returns true if rune is in 'token' as defined by RFC
// 1521 and RFC 2045.
func IsTokenChar(rune int) bool {
func IsTokenChar(r rune) bool {
// token := 1*<any (US-ASCII) CHAR except SPACE, CTLs,
// or tspecials>
return rune > 0x20 && rune < 0x7f && !isTSpecial(rune)
return r > 0x20 && r < 0x7f && !isTSpecial(r)
}
// IsToken returns true if s is a 'token' as as defined by RFC 1521
......@@ -32,14 +32,14 @@ func IsToken(s string) bool {
}
// IsQText returns true if rune is in 'qtext' as defined by RFC 822.
func IsQText(rune int) bool {
func IsQText(r int) bool {
// CHAR = <any ASCII character> ; ( 0-177, 0.-127.)
// qtext = <any CHAR excepting <">, ; => may be folded
// "\" & CR, and including
// linear-white-space>
switch rune {
switch r {
case '"', '\\', '\r':
return false
}
return rune < 0x80
return r < 0x80
}
......@@ -199,8 +199,8 @@ func decode2231Enc(v string) string {
return encv
}
func isNotTokenChar(rune int) bool {
return !IsTokenChar(rune)
func isNotTokenChar(r rune) bool {
return !IsTokenChar(r)
}
// consumeToken consumes a token from the beginning of provided
......@@ -228,24 +228,25 @@ func consumeValue(v string) (value, rest string) {
return consumeToken(v)
}
leadQuote := int(v[0])
leadQuote := rune(v[0])
// parse a quoted-string
rest = v[1:] // consume the leading quote
buffer := new(bytes.Buffer)
var idx, rune int
var idx int
var r rune
var nextIsLiteral bool
for idx, rune = range rest {
for idx, r = range rest {
switch {
case nextIsLiteral:
buffer.WriteRune(rune)
buffer.WriteRune(r)
nextIsLiteral = false
case rune == leadQuote:
case r == leadQuote:
return buffer.String(), rest[idx+1:]
case rune == '\\':
case r == '\\':
nextIsLiteral = true
case rune != '\r' && rune != '\n':
buffer.WriteRune(rune)
case r != '\r' && r != '\n':
buffer.WriteRune(r)
default:
return "", v
}
......
......@@ -18,32 +18,32 @@ func quoteWith(s string, quote byte, ASCIIonly bool) string {
var buf bytes.Buffer
buf.WriteByte(quote)
for width := 0; len(s) > 0; s = s[width:] {
rune := int(s[0])
r := rune(s[0])
width = 1
if rune >= utf8.RuneSelf {
rune, width = utf8.DecodeRuneInString(s)
if r >= utf8.RuneSelf {
r, width = utf8.DecodeRuneInString(s)
}
if width == 1 && rune == utf8.RuneError {
if width == 1 && r == utf8.RuneError {
buf.WriteString(`\x`)
buf.WriteByte(lowerhex[s[0]>>4])
buf.WriteByte(lowerhex[s[0]&0xF])
continue
}
if rune == int(quote) || rune == '\\' { // always backslashed
if r == rune(quote) || r == '\\' { // always backslashed
buf.WriteByte('\\')
buf.WriteByte(byte(rune))
buf.WriteByte(byte(r))
continue
}
if ASCIIonly {
if rune <= unicode.MaxASCII && unicode.IsPrint(rune) {
buf.WriteRune(rune)
if r <= unicode.MaxASCII && unicode.IsPrint(r) {
buf.WriteRune(r)
continue
}
} else if unicode.IsPrint(rune) {
buf.WriteRune(rune)
} else if unicode.IsPrint(r) {
buf.WriteRune(r)
continue
}
switch rune {
switch r {
case '\a':
buf.WriteString(`\a`)
case '\b':
......@@ -60,22 +60,22 @@ func quoteWith(s string, quote byte, ASCIIonly bool) string {
buf.WriteString(`\v`)
default:
switch {
case rune < ' ':
case r < ' ':
buf.WriteString(`\x`)
buf.WriteByte(lowerhex[s[0]>>4])
buf.WriteByte(lowerhex[s[0]&0xF])
case rune > unicode.MaxRune:
rune = 0xFFFD
case r > unicode.MaxRune:
r = 0xFFFD
fallthrough
case rune < 0x10000:
case r < 0x10000:
buf.WriteString(`\u`)
for s := 12; s >= 0; s -= 4 {
buf.WriteByte(lowerhex[rune>>uint(s)&0xF])
buf.WriteByte(lowerhex[r>>uint(s)&0xF])
}
default:
buf.WriteString(`\U`)
for s := 28; s >= 0; s -= 4 {
buf.WriteByte(lowerhex[rune>>uint(s)&0xF])
buf.WriteByte(lowerhex[r>>uint(s)&0xF])
}
}
}
......@@ -130,8 +130,8 @@ func CanBackquote(s string) bool {
return true
}
func unhex(b byte) (v int, ok bool) {
c := int(b)
func unhex(b byte) (v rune, ok bool) {
c := rune(b)
switch {
case '0' <= c && c <= '9':
return c - '0', true
......@@ -157,7 +157,7 @@ func unhex(b byte) (v int, ok bool) {
// If set to a single quote, it permits the sequence \' and disallows unescaped '.
// If set to a double quote, it permits \" and disallows unescaped ".
// If set to zero, it does not permit either escape and allows both quote characters to appear unescaped.
func UnquoteChar(s string, quote byte) (value int, multibyte bool, tail string, err os.Error) {
func UnquoteChar(s string, quote byte) (value rune, multibyte bool, tail string, err os.Error) {
// easy cases
switch c := s[0]; {
case c == quote && (quote == '\'' || quote == '"'):
......@@ -167,7 +167,7 @@ func UnquoteChar(s string, quote byte) (value int, multibyte bool, tail string,
r, size := utf8.DecodeRuneInString(s)
return r, true, s[size:], nil
case c != '\\':
return int(s[0]), false, s[1:], nil
return rune(s[0]), false, s[1:], nil
}
// hard case: c is backslash
......@@ -203,7 +203,7 @@ func UnquoteChar(s string, quote byte) (value int, multibyte bool, tail string,
case 'U':
n = 8
}
v := 0
var v rune
if len(s) < n {
err = os.EINVAL
return
......@@ -229,13 +229,13 @@ func UnquoteChar(s string, quote byte) (value int, multibyte bool, tail string,
value = v
multibyte = true
case '0', '1', '2', '3', '4', '5', '6', '7':
v := int(c) - '0'
v := rune(c) - '0'
if len(s) < 2 {
err = os.EINVAL
return
}
for j := 0; j < 2; j++ { // one digit already; two more
x := int(s[j]) - '0'
x := rune(s[j]) - '0'
if x < 0 || x > 7 {
return
}
......@@ -254,7 +254,7 @@ func UnquoteChar(s string, quote byte) (value int, multibyte bool, tail string,
err = os.EINVAL
return
}
value = int(c)
value = rune(c)
default:
err = os.EINVAL
return
......@@ -293,7 +293,7 @@ func Unquote(s string) (t string, err os.Error) {
}
// Is it trivial? Avoid allocation.
if strings.Index(s, `\`) < 0 && strings.IndexRune(s, int(quote)) < 0 {
if strings.Index(s, `\`) < 0 && strings.IndexRune(s, rune(quote)) < 0 {
switch quote {
case '"':
return s, nil
......
......@@ -206,7 +206,7 @@ func fieldName(original string) string {
}
return strings.Map(
func(x int) int {
func(x rune) rune {
if x == '_' || unicode.IsDigit(x) || unicode.IsLetter(x) {
return unicode.ToLower(x)
}
......
......@@ -960,13 +960,13 @@ Input:
// Decide whether the given rune is in the XML Character Range, per
// the Char production of http://www.xml.com/axml/testaxml.htm,
// Section 2.2 Characters.
func isInCharacterRange(rune int) (inrange bool) {
return rune == 0x09 ||
rune == 0x0A ||
rune == 0x0D ||
rune >= 0x20 && rune <= 0xDF77 ||
rune >= 0xE000 && rune <= 0xFFFD ||
rune >= 0x10000 && rune <= 0x10FFFF
func isInCharacterRange(r rune) (inrange bool) {
return r == 0x09 ||
r == 0x0A ||
r == 0x0D ||
r >= 0x20 && r <= 0xDF77 ||
r >= 0xE000 && r <= 0xFFFD ||
r >= 0x10000 && r <= 0x10FFFF
}
// Get name space name: name with a : stuck in the middle.
......@@ -1690,7 +1690,7 @@ func procInstEncoding(s string) string {
if v[0] != '\'' && v[0] != '"' {
return ""
}
idx = strings.IndexRune(v[1:], int(v[0]))
idx = strings.IndexRune(v[1:], rune(v[0]))
if idx == -1 {
return ""
}
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment