func()

in webdav/internal/xml/xml.go [960:1123]

• 146 lines of code
• 50 McCabe index (conditional complexity)

func (d *Decoder) text(quote int, cdata bool) []byte {
	var b0, b1 byte
	var trunc int
	d.buf.Reset()
Input:
	for {
		b, ok := d.getc()
		if !ok {
			if cdata {
				if d.err == io.EOF {
					d.err = d.syntaxError("unexpected EOF in CDATA section")
				}
				return nil
			}
			break Input
		}

		// <![CDATA[ section ends with ]]>.
		// It is an error for ]]> to appear in ordinary text.
		if b0 == ']' && b1 == ']' && b == '>' {
			if cdata {
				trunc = 2
				break Input
			}
			d.err = d.syntaxError("unescaped ]]> not in CDATA section")
			return nil
		}

		// Stop reading text if we see a <.
		if b == '<' && !cdata {
			if quote >= 0 {
				d.err = d.syntaxError("unescaped < inside quoted string")
				return nil
			}
			d.ungetc('<')
			break Input
		}
		if quote >= 0 && b == byte(quote) {
			break Input
		}
		if b == '&' && !cdata {
			// Read escaped character expression up to semicolon.
			// XML in all its glory allows a document to define and use
			// its own character names with <!ENTITY ...> directives.
			// Parsers are required to recognize lt, gt, amp, apos, and quot
			// even if they have not been declared.
			before := d.buf.Len()
			d.buf.WriteByte('&')
			var ok bool
			var text string
			var haveText bool
			if b, ok = d.mustgetc(); !ok {
				return nil
			}
			if b == '#' {
				d.buf.WriteByte(b)
				if b, ok = d.mustgetc(); !ok {
					return nil
				}
				base := 10
				if b == 'x' {
					base = 16
					d.buf.WriteByte(b)
					if b, ok = d.mustgetc(); !ok {
						return nil
					}
				}
				start := d.buf.Len()
				for '0' <= b && b <= '9' ||
					base == 16 && 'a' <= b && b <= 'f' ||
					base == 16 && 'A' <= b && b <= 'F' {
					d.buf.WriteByte(b)
					if b, ok = d.mustgetc(); !ok {
						return nil
					}
				}
				if b != ';' {
					d.ungetc(b)
				} else {
					s := string(d.buf.Bytes()[start:])
					d.buf.WriteByte(';')
					n, err := strconv.ParseUint(s, base, 64)
					if err == nil && n <= unicode.MaxRune {
						text = string(rune(n))
						haveText = true
					}
				}
			} else {
				d.ungetc(b)
				if !d.readName() {
					if d.err != nil {
						return nil
					}
					ok = false
				}
				if b, ok = d.mustgetc(); !ok {
					return nil
				}
				if b != ';' {
					d.ungetc(b)
				} else {
					name := d.buf.Bytes()[before+1:]
					d.buf.WriteByte(';')
					if isName(name) {
						s := string(name)
						if r, ok := entity[s]; ok {
							text = string(r)
							haveText = true
						} else if d.Entity != nil {
							text, haveText = d.Entity[s]
						}
					}
				}
			}

			if haveText {
				d.buf.Truncate(before)
				d.buf.Write([]byte(text))
				b0, b1 = 0, 0
				continue Input
			}
			if !d.Strict {
				b0, b1 = 0, 0
				continue Input
			}
			ent := string(d.buf.Bytes()[before:])
			if ent[len(ent)-1] != ';' {
				ent += " (no semicolon)"
			}
			d.err = d.syntaxError("invalid character entity " + ent)
			return nil
		}

		// We must rewrite unescaped \r and \r\n into \n.
		if b == '\r' {
			d.buf.WriteByte('\n')
		} else if b1 == '\r' && b == '\n' {
			// Skip \r\n--we already wrote \n.
		} else {
			d.buf.WriteByte(b)
		}

		b0, b1 = b1, b
	}
	data := d.buf.Bytes()
	data = data[0 : len(data)-trunc]

	// Inspect each rune for being a disallowed character.
	buf := data
	for len(buf) > 0 {
		r, size := utf8.DecodeRune(buf)
		if r == utf8.RuneError && size == 1 {
			d.err = d.syntaxError("invalid UTF-8")
			return nil
		}
		buf = buf[size:]
		if !isInCharacterRange(r) {
			d.err = d.syntaxError(fmt.Sprintf("illegal character code %U", r))
			return nil
		}
	}

	return data
}