Upgrade hcl to v2

Signed-off-by: Patrick Van Stee <patrick@vanstee.me>
This commit is contained in:
Patrick Van Stee
2020-04-15 21:00:17 -04:00
parent 09339bf500
commit 87c4bf1df9
129 changed files with 24573 additions and 4047 deletions

View File

@ -0,0 +1,30 @@
package textseg
import (
"bufio"
"bytes"
)
// AllTokens is a utility that uses a bufio.SplitFunc to produce a slice of
// all of the recognized tokens in the given buffer.
func AllTokens(buf []byte, splitFunc bufio.SplitFunc) ([][]byte, error) {
scanner := bufio.NewScanner(bytes.NewReader(buf))
scanner.Split(splitFunc)
var ret [][]byte
for scanner.Scan() {
ret = append(ret, scanner.Bytes())
}
return ret, scanner.Err()
}
// TokenCount is a utility that uses a bufio.SplitFunc to count the number of
// recognized tokens in the given buffer.
func TokenCount(buf []byte, splitFunc bufio.SplitFunc) (int, error) {
scanner := bufio.NewScanner(bytes.NewReader(buf))
scanner.Split(splitFunc)
var ret int
for scanner.Scan() {
ret++
}
return ret, scanner.Err()
}

View File

@ -0,0 +1,290 @@
# The following Ragel file was autogenerated with unicode2ragel.rb
# from: https://www.unicode.org/Public/emoji/12.0/emoji-data.txt
#
# It defines ["Extended_Pictographic"].
#
# To use this, make sure that your alphtype is set to byte,
# and that your input is in utf8.
%%{
machine Emoji;
Extended_Pictographic =
0xC2 0xA9 #1.1 [1] (©️) copyright
| 0xC2 0xAE #1.1 [1] (®️) registered
| 0xE2 0x80 0xBC #1.1 [1] (‼️) double exclamation mark
| 0xE2 0x81 0x89 #3.0 [1] (⁉️) exclamation question mark
| 0xE2 0x84 0xA2 #1.1 [1] (™️) trade mark
| 0xE2 0x84 0xB9 #3.0 [1] () information
| 0xE2 0x86 0x94..0x99 #1.1 [6] (↔️..↙️) left-right arrow..down...
| 0xE2 0x86 0xA9..0xAA #1.1 [2] (↩️..↪️) right arrow curving le...
| 0xE2 0x8C 0x9A..0x9B #1.1 [2] (⌚..⌛) watch..hourglass done
| 0xE2 0x8C 0xA8 #1.1 [1] (⌨️) keyboard
| 0xE2 0x8E 0x88 #3.0 [1] (⎈) HELM SYMBOL
| 0xE2 0x8F 0x8F #4.0 [1] (⏏️) eject button
| 0xE2 0x8F 0xA9..0xB3 #6.0 [11] (⏩..⏳) fast-forward button..hou...
| 0xE2 0x8F 0xB8..0xBA #7.0 [3] (⏸️..⏺️) pause button..record b...
| 0xE2 0x93 0x82 #1.1 [1] (Ⓜ️) circled M
| 0xE2 0x96 0xAA..0xAB #1.1 [2] (▪️..▫️) black small square..wh...
| 0xE2 0x96 0xB6 #1.1 [1] (▶️) play button
| 0xE2 0x97 0x80 #1.1 [1] (◀️) reverse button
| 0xE2 0x97 0xBB..0xBE #3.2 [4] (◻️..◾) white medium square..bl...
| 0xE2 0x98 0x80..0x85 #1.1 [6] (☀️..★) sun..BLACK STAR
| 0xE2 0x98 0x87..0x92 #1.1 [12] (☇..☒) LIGHTNING..BALLOT BOX WI...
| 0xE2 0x98 0x94..0x95 #4.0 [2] (☔..☕) umbrella with rain drops...
| 0xE2 0x98 0x96..0x97 #3.2 [2] (☖..☗) WHITE SHOGI PIECE..BLACK...
| 0xE2 0x98 0x98 #4.1 [1] (☘️) shamrock
| 0xE2 0x98 0x99 #3.0 [1] (☙) REVERSED ROTATED FLORAL ...
| 0xE2 0x98 0x9A..0xFF #1.1 [86] (☚..♯) BLACK LEFT POINTING INDE...
| 0xE2 0x99 0x00..0xAF #
| 0xE2 0x99 0xB0..0xB1 #3.0 [2] (♰..♱) WEST SYRIAC CROSS..EAST ...
| 0xE2 0x99 0xB2..0xBD #3.2 [12] (♲..♽) UNIVERSAL RECYCLING SYMB...
| 0xE2 0x99 0xBE..0xBF #4.1 [2] (♾️..♿) infinity..wheelchair sy...
| 0xE2 0x9A 0x80..0x85 #3.2 [6] (⚀..⚅) DIE FACE-1..DIE FACE-6
| 0xE2 0x9A 0x90..0x91 #4.0 [2] (⚐..⚑) WHITE FLAG..BLACK FLAG
| 0xE2 0x9A 0x92..0x9C #4.1 [11] (⚒️..⚜️) hammer and pick..fleur...
| 0xE2 0x9A 0x9D #5.1 [1] (⚝) OUTLINED WHITE STAR
| 0xE2 0x9A 0x9E..0x9F #5.2 [2] (⚞..⚟) THREE LINES CONVERGING R...
| 0xE2 0x9A 0xA0..0xA1 #4.0 [2] (⚠️..⚡) warning..high voltage
| 0xE2 0x9A 0xA2..0xB1 #4.1 [16] (⚢..⚱️) DOUBLED FEMALE SIGN..fu...
| 0xE2 0x9A 0xB2 #5.0 [1] (⚲) NEUTER
| 0xE2 0x9A 0xB3..0xBC #5.1 [10] (⚳..⚼) CERES..SESQUIQUADRATE
| 0xE2 0x9A 0xBD..0xBF #5.2 [3] (⚽..⚿) soccer ball..SQUARED KEY
| 0xE2 0x9B 0x80..0x83 #5.1 [4] (⛀..⛃) WHITE DRAUGHTS MAN..BLAC...
| 0xE2 0x9B 0x84..0x8D #5.2 [10] (⛄..⛍) snowman without snow..DI...
| 0xE2 0x9B 0x8E #6.0 [1] (⛎) Ophiuchus
| 0xE2 0x9B 0x8F..0xA1 #5.2 [19] (⛏️..⛡) pick..RESTRICTED LEFT E...
| 0xE2 0x9B 0xA2 #6.0 [1] (⛢) ASTRONOMICAL SYMBOL FOR ...
| 0xE2 0x9B 0xA3 #5.2 [1] (⛣) HEAVY CIRCLE WITH STROKE...
| 0xE2 0x9B 0xA4..0xA7 #6.0 [4] (⛤..⛧) PENTAGRAM..INVERTED PENT...
| 0xE2 0x9B 0xA8..0xBF #5.2 [24] (⛨..⛿) BLACK CROSS ON SHIELD..W...
| 0xE2 0x9C 0x80 #7.0 [1] (✀) BLACK SAFETY SCISSORS
| 0xE2 0x9C 0x81..0x84 #1.1 [4] (✁..✄) UPPER BLADE SCISSORS..WH...
| 0xE2 0x9C 0x85 #6.0 [1] (✅) check mark button
| 0xE2 0x9C 0x88..0x89 #1.1 [2] (✈️..✉️) airplane..envelope
| 0xE2 0x9C 0x8A..0x8B #6.0 [2] (✊..✋) raised fist..raised hand
| 0xE2 0x9C 0x8C..0x92 #1.1 [7] (✌️..✒️) victory hand..black nib
| 0xE2 0x9C 0x94 #1.1 [1] (✔️) check mark
| 0xE2 0x9C 0x96 #1.1 [1] (✖️) multiplication sign
| 0xE2 0x9C 0x9D #1.1 [1] (✝️) latin cross
| 0xE2 0x9C 0xA1 #1.1 [1] (✡️) star of David
| 0xE2 0x9C 0xA8 #6.0 [1] (✨) sparkles
| 0xE2 0x9C 0xB3..0xB4 #1.1 [2] (✳️..✴️) eight-spoked asterisk....
| 0xE2 0x9D 0x84 #1.1 [1] (❄️) snowflake
| 0xE2 0x9D 0x87 #1.1 [1] (❇️) sparkle
| 0xE2 0x9D 0x8C #6.0 [1] (❌) cross mark
| 0xE2 0x9D 0x8E #6.0 [1] (❎) cross mark button
| 0xE2 0x9D 0x93..0x95 #6.0 [3] (❓..❕) question mark..white exc...
| 0xE2 0x9D 0x97 #5.2 [1] (❗) exclamation mark
| 0xE2 0x9D 0xA3..0xA7 #1.1 [5] (❣️..❧) heart exclamation..ROTA...
| 0xE2 0x9E 0x95..0x97 #6.0 [3] (..➗) plus sign..division sign
| 0xE2 0x9E 0xA1 #1.1 [1] (➡️) right arrow
| 0xE2 0x9E 0xB0 #6.0 [1] (➰) curly loop
| 0xE2 0x9E 0xBF #6.0 [1] (➿) double curly loop
| 0xE2 0xA4 0xB4..0xB5 #3.2 [2] (⤴️..⤵️) right arrow curving up...
| 0xE2 0xAC 0x85..0x87 #4.0 [3] (⬅️..⬇️) left arrow..down arrow
| 0xE2 0xAC 0x9B..0x9C #5.1 [2] (⬛..⬜) black large square..whit...
| 0xE2 0xAD 0x90 #5.1 [1] (⭐) star
| 0xE2 0xAD 0x95 #5.2 [1] (⭕) hollow red circle
| 0xE3 0x80 0xB0 #1.1 [1] (〰️) wavy dash
| 0xE3 0x80 0xBD #3.2 [1] (〽️) part alternation mark
| 0xE3 0x8A 0x97 #1.1 [1] (㊗️) Japanese “congratulatio...
| 0xE3 0x8A 0x99 #1.1 [1] (㊙️) Japanese “secret” button
| 0xF0 0x9F 0x80 0x80..0xAB #5.1 [44] (🀀..🀫) MAHJONG TILE EAST WIN...
| 0xF0 0x9F 0x80 0xAC..0xAF #NA [4] (🀬..🀯) <reserved-1F02C>..<res...
| 0xF0 0x9F 0x80 0xB0..0xFF #5.1[100] (🀰..🂓) DOMINO TILE HOR...
| 0xF0 0x9F 0x81..0x81 0x00..0xFF #
| 0xF0 0x9F 0x82 0x00..0x93 #
| 0xF0 0x9F 0x82 0x94..0x9F #NA [12] (🂔..🂟) <reserved-1F094>..<res...
| 0xF0 0x9F 0x82 0xA0..0xAE #6.0 [15] (🂠..🂮) PLAYING CARD BACK..PL...
| 0xF0 0x9F 0x82 0xAF..0xB0 #NA [2] (🂯..🂰) <reserved-1F0AF>..<res...
| 0xF0 0x9F 0x82 0xB1..0xBE #6.0 [14] (🂱..🂾) PLAYING CARD ACE OF H...
| 0xF0 0x9F 0x82 0xBF #7.0 [1] (🂿) PLAYING CARD RED JOKER
| 0xF0 0x9F 0x83 0x80 #NA [1] (🃀) <reserved-1F0C0>
| 0xF0 0x9F 0x83 0x81..0x8F #6.0 [15] (🃁..🃏) PLAYING CARD ACE OF D...
| 0xF0 0x9F 0x83 0x90 #NA [1] (🃐) <reserved-1F0D0>
| 0xF0 0x9F 0x83 0x91..0x9F #6.0 [15] (🃑..🃟) PLAYING CARD ACE OF C...
| 0xF0 0x9F 0x83 0xA0..0xB5 #7.0 [22] (🃠..🃵) PLAYING CARD FOOL..PL...
| 0xF0 0x9F 0x83 0xB6..0xBF #NA [10] (🃶..🃿) <reserved-1F0F6>..<res...
| 0xF0 0x9F 0x84 0x8D..0x8F #NA [3] (🄍..🄏) <reserved-1F10D>..<res...
| 0xF0 0x9F 0x84 0xAF #11.0 [1] (🄯) COPYLEFT SYMBOL
| 0xF0 0x9F 0x85 0xAC #12.0 [1] (🅬) RAISED MR SIGN
| 0xF0 0x9F 0x85 0xAD..0xAF #NA [3] (🅭..🅯) <reserved-1F16D>..<res...
| 0xF0 0x9F 0x85 0xB0..0xB1 #6.0 [2] (🅰️..🅱️) A button (blood typ...
| 0xF0 0x9F 0x85 0xBE #6.0 [1] (🅾️) O button (blood type)
| 0xF0 0x9F 0x85 0xBF #5.2 [1] (🅿️) P button
| 0xF0 0x9F 0x86 0x8E #6.0 [1] (🆎) AB button (blood type)
| 0xF0 0x9F 0x86 0x91..0x9A #6.0 [10] (🆑..🆚) CL button..VS button
| 0xF0 0x9F 0x86 0xAD..0xFF #NA [57] (🆭..🇥) <reserved-1F1AD>..<res...
| 0xF0 0x9F 0x87 0x00..0xA5 #
| 0xF0 0x9F 0x88 0x81..0x82 #6.0 [2] (🈁..🈂️) Japanese “here” butt...
| 0xF0 0x9F 0x88 0x83..0x8F #NA [13] (🈃..🈏) <reserved-1F203>..<res...
| 0xF0 0x9F 0x88 0x9A #5.2 [1] (🈚) Japanese “free of charge...
| 0xF0 0x9F 0x88 0xAF #5.2 [1] (🈯) Japanese “reserved” button
| 0xF0 0x9F 0x88 0xB2..0xBA #6.0 [9] (🈲..🈺) Japanese “prohibited”...
| 0xF0 0x9F 0x88 0xBC..0xBF #NA [4] (🈼..🈿) <reserved-1F23C>..<res...
| 0xF0 0x9F 0x89 0x89..0x8F #NA [7] (🉉..🉏) <reserved-1F249>..<res...
| 0xF0 0x9F 0x89 0x90..0x91 #6.0 [2] (🉐..🉑) Japanese “bargain” bu...
| 0xF0 0x9F 0x89 0x92..0x9F #NA [14] (🉒..🉟) <reserved-1F252>..<res...
| 0xF0 0x9F 0x89 0xA0..0xA5 #10.0 [6] (🉠..🉥) ROUNDED SYMBOL FOR F...
| 0xF0 0x9F 0x89 0xA6..0xFF #NA[154] (🉦..🋿) <reserved-1F266>...
| 0xF0 0x9F 0x8A..0x8A 0x00..0xFF #
| 0xF0 0x9F 0x8B 0x00..0xBF #
| 0xF0 0x9F 0x8C 0x80..0xA0 #6.0 [33] (🌀..🌠) cyclone..shooting star
| 0xF0 0x9F 0x8C 0xA1..0xAC #7.0 [12] (🌡️..🌬️) thermometer..wind face
| 0xF0 0x9F 0x8C 0xAD..0xAF #8.0 [3] (🌭..🌯) hot dog..burrito
| 0xF0 0x9F 0x8C 0xB0..0xB5 #6.0 [6] (🌰..🌵) chestnut..cactus
| 0xF0 0x9F 0x8C 0xB6 #7.0 [1] (🌶️) hot pepper
| 0xF0 0x9F 0x8C 0xB7..0xFF #6.0 [70] (🌷..🍼) tulip..baby bottle
| 0xF0 0x9F 0x8D 0x00..0xBC #
| 0xF0 0x9F 0x8D 0xBD #7.0 [1] (🍽️) fork and knife with plate
| 0xF0 0x9F 0x8D 0xBE..0xBF #8.0 [2] (🍾..🍿) bottle with popping c...
| 0xF0 0x9F 0x8E 0x80..0x93 #6.0 [20] (🎀..🎓) ribbon..graduation cap
| 0xF0 0x9F 0x8E 0x94..0x9F #7.0 [12] (🎔..🎟️) HEART WITH TIP ON TH...
| 0xF0 0x9F 0x8E 0xA0..0xFF #6.0 [37] (🎠..🏄) carousel horse..perso...
| 0xF0 0x9F 0x8F 0x00..0x84 #
| 0xF0 0x9F 0x8F 0x85 #7.0 [1] (🏅) sports medal
| 0xF0 0x9F 0x8F 0x86..0x8A #6.0 [5] (🏆..🏊) trophy..person swimming
| 0xF0 0x9F 0x8F 0x8B..0x8E #7.0 [4] (🏋️..🏎️) person lifting weig...
| 0xF0 0x9F 0x8F 0x8F..0x93 #8.0 [5] (🏏..🏓) cricket game..ping pong
| 0xF0 0x9F 0x8F 0x94..0x9F #7.0 [12] (🏔️..🏟️) snow-capped mountai...
| 0xF0 0x9F 0x8F 0xA0..0xB0 #6.0 [17] (🏠..🏰) house..castle
| 0xF0 0x9F 0x8F 0xB1..0xB7 #7.0 [7] (🏱..🏷️) WHITE PENNANT..label
| 0xF0 0x9F 0x8F 0xB8..0xBA #8.0 [3] (🏸..🏺) badminton..amphora
| 0xF0 0x9F 0x90 0x80..0xBE #6.0 [63] (🐀..🐾) rat..paw prints
| 0xF0 0x9F 0x90 0xBF #7.0 [1] (🐿️) chipmunk
| 0xF0 0x9F 0x91 0x80 #6.0 [1] (👀) eyes
| 0xF0 0x9F 0x91 0x81 #7.0 [1] (👁️) eye
| 0xF0 0x9F 0x91 0x82..0xFF #6.0[182] (👂..📷) ear..camera
| 0xF0 0x9F 0x92..0x92 0x00..0xFF #
| 0xF0 0x9F 0x93 0x00..0xB7 #
| 0xF0 0x9F 0x93 0xB8 #7.0 [1] (📸) camera with flash
| 0xF0 0x9F 0x93 0xB9..0xBC #6.0 [4] (📹..📼) video camera..videoca...
| 0xF0 0x9F 0x93 0xBD..0xBE #7.0 [2] (📽️..📾) film projector..PORT...
| 0xF0 0x9F 0x93 0xBF #8.0 [1] (📿) prayer beads
| 0xF0 0x9F 0x94 0x80..0xBD #6.0 [62] (🔀..🔽) shuffle tracks button...
| 0xF0 0x9F 0x95 0x86..0x8A #7.0 [5] (🕆..🕊️) WHITE LATIN CROSS..dove
| 0xF0 0x9F 0x95 0x8B..0x8F #8.0 [5] (🕋..🕏) kaaba..BOWL OF HYGIEIA
| 0xF0 0x9F 0x95 0x90..0xA7 #6.0 [24] (🕐..🕧) one oclock..twelve-t...
| 0xF0 0x9F 0x95 0xA8..0xB9 #7.0 [18] (🕨..🕹️) RIGHT SPEAKER..joystick
| 0xF0 0x9F 0x95 0xBA #9.0 [1] (🕺) man dancing
| 0xF0 0x9F 0x95 0xBB..0xFF #7.0 [41] (🕻..🖣) LEFT HAND TELEPHONE R...
| 0xF0 0x9F 0x96 0x00..0xA3 #
| 0xF0 0x9F 0x96 0xA4 #9.0 [1] (🖤) black heart
| 0xF0 0x9F 0x96 0xA5..0xFF #7.0 [86] (🖥️..🗺️) desktop computer..w...
| 0xF0 0x9F 0x97 0x00..0xBA #
| 0xF0 0x9F 0x97 0xBB..0xBF #6.0 [5] (🗻..🗿) mount fuji..moai
| 0xF0 0x9F 0x98 0x80 #6.1 [1] (😀) grinning face
| 0xF0 0x9F 0x98 0x81..0x90 #6.0 [16] (😁..😐) beaming face with smi...
| 0xF0 0x9F 0x98 0x91 #6.1 [1] (😑) expressionless face
| 0xF0 0x9F 0x98 0x92..0x94 #6.0 [3] (😒..😔) unamused face..pensiv...
| 0xF0 0x9F 0x98 0x95 #6.1 [1] (😕) confused face
| 0xF0 0x9F 0x98 0x96 #6.0 [1] (😖) confounded face
| 0xF0 0x9F 0x98 0x97 #6.1 [1] (😗) kissing face
| 0xF0 0x9F 0x98 0x98 #6.0 [1] (😘) face blowing a kiss
| 0xF0 0x9F 0x98 0x99 #6.1 [1] (😙) kissing face with smilin...
| 0xF0 0x9F 0x98 0x9A #6.0 [1] (😚) kissing face with closed...
| 0xF0 0x9F 0x98 0x9B #6.1 [1] (😛) face with tongue
| 0xF0 0x9F 0x98 0x9C..0x9E #6.0 [3] (😜..😞) winking face with ton...
| 0xF0 0x9F 0x98 0x9F #6.1 [1] (😟) worried face
| 0xF0 0x9F 0x98 0xA0..0xA5 #6.0 [6] (😠..😥) angry face..sad but r...
| 0xF0 0x9F 0x98 0xA6..0xA7 #6.1 [2] (😦..😧) frowning face with op...
| 0xF0 0x9F 0x98 0xA8..0xAB #6.0 [4] (😨..😫) fearful face..tired face
| 0xF0 0x9F 0x98 0xAC #6.1 [1] (😬) grimacing face
| 0xF0 0x9F 0x98 0xAD #6.0 [1] (😭) loudly crying face
| 0xF0 0x9F 0x98 0xAE..0xAF #6.1 [2] (😮..😯) face with open mouth....
| 0xF0 0x9F 0x98 0xB0..0xB3 #6.0 [4] (😰..😳) anxious face with swe...
| 0xF0 0x9F 0x98 0xB4 #6.1 [1] (😴) sleeping face
| 0xF0 0x9F 0x98 0xB5..0xFF #6.0 [12] (😵..🙀) dizzy face..weary cat
| 0xF0 0x9F 0x99 0x00..0x80 #
| 0xF0 0x9F 0x99 0x81..0x82 #7.0 [2] (🙁..🙂) slightly frowning fac...
| 0xF0 0x9F 0x99 0x83..0x84 #8.0 [2] (🙃..🙄) upside-down face..fac...
| 0xF0 0x9F 0x99 0x85..0x8F #6.0 [11] (🙅..🙏) person gesturing NO.....
| 0xF0 0x9F 0x9A 0x80..0xFF #6.0 [70] (🚀..🛅) rocket..left luggage
| 0xF0 0x9F 0x9B 0x00..0x85 #
| 0xF0 0x9F 0x9B 0x86..0x8F #7.0 [10] (🛆..🛏️) TRIANGLE WITH ROUNDE...
| 0xF0 0x9F 0x9B 0x90 #8.0 [1] (🛐) place of worship
| 0xF0 0x9F 0x9B 0x91..0x92 #9.0 [2] (🛑..🛒) stop sign..shopping cart
| 0xF0 0x9F 0x9B 0x93..0x94 #10.0 [2] (🛓..🛔) STUPA..PAGODA
| 0xF0 0x9F 0x9B 0x95 #12.0 [1] (🛕) hindu temple
| 0xF0 0x9F 0x9B 0x96..0x9F #NA [10] (🛖..🛟) <reserved-1F6D6>..<res...
| 0xF0 0x9F 0x9B 0xA0..0xAC #7.0 [13] (🛠️..🛬) hammer and wrench..a...
| 0xF0 0x9F 0x9B 0xAD..0xAF #NA [3] (🛭..🛯) <reserved-1F6ED>..<res...
| 0xF0 0x9F 0x9B 0xB0..0xB3 #7.0 [4] (🛰️..🛳️) satellite..passenge...
| 0xF0 0x9F 0x9B 0xB4..0xB6 #9.0 [3] (🛴..🛶) kick scooter..canoe
| 0xF0 0x9F 0x9B 0xB7..0xB8 #10.0 [2] (🛷..🛸) sled..flying saucer
| 0xF0 0x9F 0x9B 0xB9 #11.0 [1] (🛹) skateboard
| 0xF0 0x9F 0x9B 0xBA #12.0 [1] (🛺) auto rickshaw
| 0xF0 0x9F 0x9B 0xBB..0xBF #NA [5] (🛻..🛿) <reserved-1F6FB>..<res...
| 0xF0 0x9F 0x9D 0xB4..0xBF #NA [12] (🝴..🝿) <reserved-1F774>..<res...
| 0xF0 0x9F 0x9F 0x95..0x98 #11.0 [4] (🟕..🟘) CIRCLED TRIANGLE..NE...
| 0xF0 0x9F 0x9F 0x99..0x9F #NA [7] (🟙..🟟) <reserved-1F7D9>..<res...
| 0xF0 0x9F 0x9F 0xA0..0xAB #12.0 [12] (🟠..🟫) orange circle..brown...
| 0xF0 0x9F 0x9F 0xAC..0xBF #NA [20] (🟬..🟿) <reserved-1F7EC>..<res...
| 0xF0 0x9F 0xA0 0x8C..0x8F #NA [4] (🠌..🠏) <reserved-1F80C>..<res...
| 0xF0 0x9F 0xA1 0x88..0x8F #NA [8] (🡈..🡏) <reserved-1F848>..<res...
| 0xF0 0x9F 0xA1 0x9A..0x9F #NA [6] (🡚..🡟) <reserved-1F85A>..<res...
| 0xF0 0x9F 0xA2 0x88..0x8F #NA [8] (🢈..🢏) <reserved-1F888>..<res...
| 0xF0 0x9F 0xA2 0xAE..0xFF #NA [82] (🢮..🣿) <reserved-1F8AE>..<res...
| 0xF0 0x9F 0xA3 0x00..0xBF #
| 0xF0 0x9F 0xA4 0x8C #NA [1] (🤌) <reserved-1F90C>
| 0xF0 0x9F 0xA4 0x8D..0x8F #12.0 [3] (🤍..🤏) white heart..pinchin...
| 0xF0 0x9F 0xA4 0x90..0x98 #8.0 [9] (🤐..🤘) zipper-mouth face..si...
| 0xF0 0x9F 0xA4 0x99..0x9E #9.0 [6] (🤙..🤞) call me hand..crossed...
| 0xF0 0x9F 0xA4 0x9F #10.0 [1] (🤟) love-you gesture
| 0xF0 0x9F 0xA4 0xA0..0xA7 #9.0 [8] (🤠..🤧) cowboy hat face..snee...
| 0xF0 0x9F 0xA4 0xA8..0xAF #10.0 [8] (🤨..🤯) face with raised eye...
| 0xF0 0x9F 0xA4 0xB0 #9.0 [1] (🤰) pregnant woman
| 0xF0 0x9F 0xA4 0xB1..0xB2 #10.0 [2] (🤱..🤲) breast-feeding..palm...
| 0xF0 0x9F 0xA4 0xB3..0xBA #9.0 [8] (🤳..🤺) selfie..person fencing
| 0xF0 0x9F 0xA4 0xBC..0xBE #9.0 [3] (🤼..🤾) people wrestling..per...
| 0xF0 0x9F 0xA4 0xBF #12.0 [1] (🤿) diving mask
| 0xF0 0x9F 0xA5 0x80..0x85 #9.0 [6] (🥀..🥅) wilted flower..goal net
| 0xF0 0x9F 0xA5 0x87..0x8B #9.0 [5] (🥇..🥋) 1st place medal..mart...
| 0xF0 0x9F 0xA5 0x8C #10.0 [1] (🥌) curling stone
| 0xF0 0x9F 0xA5 0x8D..0x8F #11.0 [3] (🥍..🥏) lacrosse..flying disc
| 0xF0 0x9F 0xA5 0x90..0x9E #9.0 [15] (🥐..🥞) croissant..pancakes
| 0xF0 0x9F 0xA5 0x9F..0xAB #10.0 [13] (🥟..🥫) dumpling..canned food
| 0xF0 0x9F 0xA5 0xAC..0xB0 #11.0 [5] (🥬..🥰) leafy green..smiling...
| 0xF0 0x9F 0xA5 0xB1 #12.0 [1] (🥱) yawning face
| 0xF0 0x9F 0xA5 0xB2 #NA [1] (🥲) <reserved-1F972>
| 0xF0 0x9F 0xA5 0xB3..0xB6 #11.0 [4] (🥳..🥶) partying face..cold ...
| 0xF0 0x9F 0xA5 0xB7..0xB9 #NA [3] (🥷..🥹) <reserved-1F977>..<res...
| 0xF0 0x9F 0xA5 0xBA #11.0 [1] (🥺) pleading face
| 0xF0 0x9F 0xA5 0xBB #12.0 [1] (🥻) sari
| 0xF0 0x9F 0xA5 0xBC..0xBF #11.0 [4] (🥼..🥿) lab coat..flat shoe
| 0xF0 0x9F 0xA6 0x80..0x84 #8.0 [5] (🦀..🦄) crab..unicorn
| 0xF0 0x9F 0xA6 0x85..0x91 #9.0 [13] (🦅..🦑) eagle..squid
| 0xF0 0x9F 0xA6 0x92..0x97 #10.0 [6] (🦒..🦗) giraffe..cricket
| 0xF0 0x9F 0xA6 0x98..0xA2 #11.0 [11] (🦘..🦢) kangaroo..swan
| 0xF0 0x9F 0xA6 0xA3..0xA4 #NA [2] (🦣..🦤) <reserved-1F9A3>..<res...
| 0xF0 0x9F 0xA6 0xA5..0xAA #12.0 [6] (🦥..🦪) sloth..oyster
| 0xF0 0x9F 0xA6 0xAB..0xAD #NA [3] (🦫..🦭) <reserved-1F9AB>..<res...
| 0xF0 0x9F 0xA6 0xAE..0xAF #12.0 [2] (🦮..🦯) guide dog..probing cane
| 0xF0 0x9F 0xA6 0xB0..0xB9 #11.0 [10] (🦰..🦹) red hair..supervillain
| 0xF0 0x9F 0xA6 0xBA..0xBF #12.0 [6] (🦺..🦿) safety vest..mechani...
| 0xF0 0x9F 0xA7 0x80 #8.0 [1] (🧀) cheese wedge
| 0xF0 0x9F 0xA7 0x81..0x82 #11.0 [2] (🧁..🧂) cupcake..salt
| 0xF0 0x9F 0xA7 0x83..0x8A #12.0 [8] (🧃..🧊) beverage box..ice cube
| 0xF0 0x9F 0xA7 0x8B..0x8C #NA [2] (🧋..🧌) <reserved-1F9CB>..<res...
| 0xF0 0x9F 0xA7 0x8D..0x8F #12.0 [3] (🧍..🧏) person standing..dea...
| 0xF0 0x9F 0xA7 0x90..0xA6 #10.0 [23] (🧐..🧦) face with monocle..s...
| 0xF0 0x9F 0xA7 0xA7..0xBF #11.0 [25] (🧧..🧿) red envelope..nazar ...
| 0xF0 0x9F 0xA8 0x80..0xFF #12.0 [84] (🨀..🩓) NEUTRAL CHESS KING.....
| 0xF0 0x9F 0xA9 0x00..0x93 #
| 0xF0 0x9F 0xA9 0x94..0x9F #NA [12] (🩔..🩟) <reserved-1FA54>..<res...
| 0xF0 0x9F 0xA9 0xA0..0xAD #11.0 [14] (🩠..🩭) XIANGQI RED GENERAL....
| 0xF0 0x9F 0xA9 0xAE..0xAF #NA [2] (🩮..🩯) <reserved-1FA6E>..<res...
| 0xF0 0x9F 0xA9 0xB0..0xB3 #12.0 [4] (🩰..🩳) ballet shoes..shorts
| 0xF0 0x9F 0xA9 0xB4..0xB7 #NA [4] (🩴..🩷) <reserved-1FA74>..<res...
| 0xF0 0x9F 0xA9 0xB8..0xBA #12.0 [3] (🩸..🩺) drop of blood..steth...
| 0xF0 0x9F 0xA9 0xBB..0xBF #NA [5] (🩻..🩿) <reserved-1FA7B>..<res...
| 0xF0 0x9F 0xAA 0x80..0x82 #12.0 [3] (🪀..🪂) yo-yo..parachute
| 0xF0 0x9F 0xAA 0x83..0x8F #NA [13] (🪃..🪏) <reserved-1FA83>..<res...
| 0xF0 0x9F 0xAA 0x90..0x95 #12.0 [6] (🪐..🪕) ringed planet..banjo
| 0xF0 0x9F 0xAA 0x96..0xFF #NA[1384] (🪖..🿽) <reserved-1FA96>...
| 0xF0 0x9F 0xAB..0xBE 0x00..0xFF #
| 0xF0 0x9F 0xBF 0x00..0xBD #
;
}%%

View File

@ -0,0 +1,8 @@
package textseg
//go:generate go run make_tables.go -output tables.go
//go:generate go run make_test_tables.go -output tables_test.go
//go:generate ruby unicode2ragel.rb --url=https://www.unicode.org/Public/12.0.0/ucd/auxiliary/GraphemeBreakProperty.txt -m GraphemeCluster -p "Prepend,CR,LF,Control,Extend,Regional_Indicator,SpacingMark,L,V,T,LV,LVT,ZWJ" -o grapheme_clusters_table.rl
//go:generate ruby unicode2ragel.rb --url=https://www.unicode.org/Public/emoji/12.0/emoji-data.txt -m Emoji -p "Extended_Pictographic" -o emoji_table.rl
//go:generate ragel -Z grapheme_clusters.rl
//go:generate gofmt -w grapheme_clusters.go

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,133 @@
package textseg
import (
"errors"
"unicode/utf8"
)
// Generated from grapheme_clusters.rl. DO NOT EDIT
%%{
# (except you are actually in grapheme_clusters.rl here, so edit away!)
machine graphclust;
write data;
}%%
var Error = errors.New("invalid UTF8 text")
// ScanGraphemeClusters is a split function for bufio.Scanner that splits
// on grapheme cluster boundaries.
func ScanGraphemeClusters(data []byte, atEOF bool) (int, []byte, error) {
if len(data) == 0 {
return 0, nil, nil
}
// Ragel state
cs := 0 // Current State
p := 0 // "Pointer" into data
pe := len(data) // End-of-data "pointer"
ts := 0
te := 0
act := 0
eof := pe
// Make Go compiler happy
_ = ts
_ = te
_ = act
_ = eof
startPos := 0
endPos := 0
%%{
include GraphemeCluster "grapheme_clusters_table.rl";
include Emoji "emoji_table.rl";
action start {
startPos = p
}
action end {
endPos = p
}
action emit {
return endPos+1, data[startPos:endPos+1], nil
}
ZWJGlue = ZWJ (Extended_Pictographic Extend*)?;
AnyExtender = Extend | ZWJGlue | SpacingMark;
Extension = AnyExtender*;
ReplacementChar = (0xEF 0xBF 0xBD);
CRLFSeq = CR LF;
ControlSeq = Control | ReplacementChar;
HangulSeq = (
L+ (((LV? V+ | LVT) T*)?|LV?) |
LV V* T* |
V+ T* |
LVT T* |
T+
) Extension;
EmojiSeq = Extended_Pictographic Extend* Extension;
ZWJSeq = ZWJ (ZWJ | Extend | SpacingMark)*;
EmojiFlagSeq = Regional_Indicator Regional_Indicator? Extension;
UTF8Cont = 0x80 .. 0xBF;
AnyUTF8 = (
0x00..0x7F |
0xC0..0xDF . UTF8Cont |
0xE0..0xEF . UTF8Cont . UTF8Cont |
0xF0..0xF7 . UTF8Cont . UTF8Cont . UTF8Cont
);
# OtherSeq is any character that isn't at the start of one of the extended sequences above, followed by extension
OtherSeq = (AnyUTF8 - (CR|LF|Control|ReplacementChar|L|LV|V|LVT|T|Extended_Pictographic|ZWJ|Regional_Indicator|Prepend)) (Extend | ZWJ | SpacingMark)*;
# PrependSeq is prepend followed by any of the other patterns above, except control characters which explicitly break
PrependSeq = Prepend+ (HangulSeq|EmojiSeq|ZWJSeq|EmojiFlagSeq|OtherSeq)?;
CRLFTok = CRLFSeq >start @end;
ControlTok = ControlSeq >start @end;
HangulTok = HangulSeq >start @end;
EmojiTok = EmojiSeq >start @end;
ZWJTok = ZWJSeq >start @end;
EmojiFlagTok = EmojiFlagSeq >start @end;
OtherTok = OtherSeq >start @end;
PrependTok = PrependSeq >start @end;
main := |*
CRLFTok => emit;
ControlTok => emit;
HangulTok => emit;
EmojiTok => emit;
ZWJTok => emit;
EmojiFlagTok => emit;
PrependTok => emit;
OtherTok => emit;
# any single valid UTF-8 character would also be valid per spec,
# but we'll handle that separately after the loop so we can deal
# with requesting more bytes if we're not at EOF.
*|;
write init;
write exec;
}%%
// If we fall out here then we were unable to complete a sequence.
// If we weren't able to complete a sequence then either we've
// reached the end of a partial buffer (so there's more data to come)
// or we have an isolated symbol that would normally be part of a
// grapheme cluster but has appeared in isolation here.
if !atEOF {
// Request more
return 0, nil, nil
}
// Just take the first UTF-8 sequence and return that.
_, seqLen := utf8.DecodeRune(data)
return seqLen, data[:seqLen], nil
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,335 @@
#!/usr/bin/env ruby
#
# This scripted has been updated to accept more command-line arguments:
#
# -u, --url URL to process
# -m, --machine Machine name
# -p, --properties Properties to add to the machine
# -o, --output Write output to file
#
# Updated by: Marty Schoch <marty.schoch@gmail.com>
#
# This script uses the unicode spec to generate a Ragel state machine
# that recognizes unicode alphanumeric characters. It generates 5
# character classes: uupper, ulower, ualpha, udigit, and ualnum.
# Currently supported encodings are UTF-8 [default] and UCS-4.
#
# Usage: unicode2ragel.rb [options]
# -e, --encoding [ucs4 | utf8] Data encoding
# -h, --help Show this message
#
# This script was originally written as part of the Ferret search
# engine library.
#
# Author: Rakan El-Khalil <rakan@well.com>
require 'optparse'
require 'open-uri'
ENCODINGS = [ :utf8, :ucs4 ]
ALPHTYPES = { :utf8 => "byte", :ucs4 => "rune" }
DEFAULT_CHART_URL = "http://www.unicode.org/Public/5.1.0/ucd/DerivedCoreProperties.txt"
DEFAULT_MACHINE_NAME= "WChar"
###
# Display vars & default option
TOTAL_WIDTH = 80
RANGE_WIDTH = 23
@encoding = :utf8
@chart_url = DEFAULT_CHART_URL
machine_name = DEFAULT_MACHINE_NAME
properties = []
@output = $stdout
###
# Option parsing
cli_opts = OptionParser.new do |opts|
opts.on("-e", "--encoding [ucs4 | utf8]", "Data encoding") do |o|
@encoding = o.downcase.to_sym
end
opts.on("-h", "--help", "Show this message") do
puts opts
exit
end
opts.on("-u", "--url URL", "URL to process") do |o|
@chart_url = o
end
opts.on("-m", "--machine MACHINE_NAME", "Machine name") do |o|
machine_name = o
end
opts.on("-p", "--properties x,y,z", Array, "Properties to add to machine") do |o|
properties = o
end
opts.on("-o", "--output FILE", "output file") do |o|
@output = File.new(o, "w+")
end
end
cli_opts.parse(ARGV)
unless ENCODINGS.member? @encoding
puts "Invalid encoding: #{@encoding}"
puts cli_opts
exit
end
##
# Downloads the document at url and yields every alpha line's hex
# range and description.
def each_alpha( url, property )
open( url ) do |file|
file.each_line do |line|
next if line =~ /^#/;
next if line !~ /; #{property} *#/;
range, description = line.split(/;/)
range.strip!
description.gsub!(/.*#/, '').strip!
if range =~ /\.\./
start, stop = range.split '..'
else start = stop = range
end
yield start.hex .. stop.hex, description
end
end
end
###
# Formats to hex at minimum width
def to_hex( n )
r = "%0X" % n
r = "0#{r}" unless (r.length % 2).zero?
r
end
###
# UCS4 is just a straight hex conversion of the unicode codepoint.
def to_ucs4( range )
rangestr = "0x" + to_hex(range.begin)
rangestr << "..0x" + to_hex(range.end) if range.begin != range.end
[ rangestr ]
end
##
# 0x00 - 0x7f -> 0zzzzzzz[7]
# 0x80 - 0x7ff -> 110yyyyy[5] 10zzzzzz[6]
# 0x800 - 0xffff -> 1110xxxx[4] 10yyyyyy[6] 10zzzzzz[6]
# 0x010000 - 0x10ffff -> 11110www[3] 10xxxxxx[6] 10yyyyyy[6] 10zzzzzz[6]
UTF8_BOUNDARIES = [0x7f, 0x7ff, 0xffff, 0x10ffff]
def to_utf8_enc( n )
r = 0
if n <= 0x7f
r = n
elsif n <= 0x7ff
y = 0xc0 | (n >> 6)
z = 0x80 | (n & 0x3f)
r = y << 8 | z
elsif n <= 0xffff
x = 0xe0 | (n >> 12)
y = 0x80 | (n >> 6) & 0x3f
z = 0x80 | n & 0x3f
r = x << 16 | y << 8 | z
elsif n <= 0x10ffff
w = 0xf0 | (n >> 18)
x = 0x80 | (n >> 12) & 0x3f
y = 0x80 | (n >> 6) & 0x3f
z = 0x80 | n & 0x3f
r = w << 24 | x << 16 | y << 8 | z
end
to_hex(r)
end
def from_utf8_enc( n )
n = n.hex
r = 0
if n <= 0x7f
r = n
elsif n <= 0xdfff
y = (n >> 8) & 0x1f
z = n & 0x3f
r = y << 6 | z
elsif n <= 0xefffff
x = (n >> 16) & 0x0f
y = (n >> 8) & 0x3f
z = n & 0x3f
r = x << 10 | y << 6 | z
elsif n <= 0xf7ffffff
w = (n >> 24) & 0x07
x = (n >> 16) & 0x3f
y = (n >> 8) & 0x3f
z = n & 0x3f
r = w << 18 | x << 12 | y << 6 | z
end
r
end
###
# Given a range, splits it up into ranges that can be continuously
# encoded into utf8. Eg: 0x00 .. 0xff => [0x00..0x7f, 0x80..0xff]
# This is not strictly needed since the current [5.1] unicode standard
# doesn't have ranges that straddle utf8 boundaries. This is included
# for completeness as there is no telling if that will ever change.
def utf8_ranges( range )
ranges = []
UTF8_BOUNDARIES.each do |max|
if range.begin <= max
if range.end <= max
ranges << range
return ranges
end
ranges << (range.begin .. max)
range = (max + 1) .. range.end
end
end
ranges
end
def build_range( start, stop )
size = start.size/2
left = size - 1
return [""] if size < 1
a = start[0..1]
b = stop[0..1]
###
# Shared prefix
if a == b
return build_range(start[2..-1], stop[2..-1]).map do |elt|
"0x#{a} " + elt
end
end
###
# Unshared prefix, end of run
return ["0x#{a}..0x#{b} "] if left.zero?
###
# Unshared prefix, not end of run
# Range can be 0x123456..0x56789A
# Which is equivalent to:
# 0x123456 .. 0x12FFFF
# 0x130000 .. 0x55FFFF
# 0x560000 .. 0x56789A
ret = []
ret << build_range(start, a + "FF" * left)
###
# Only generate middle range if need be.
if a.hex+1 != b.hex
max = to_hex(b.hex - 1)
max = "FF" if b == "FF"
ret << "0x#{to_hex(a.hex+1)}..0x#{max} " + "0x00..0xFF " * left
end
###
# Don't generate last range if it is covered by first range
ret << build_range(b + "00" * left, stop) unless b == "FF"
ret.flatten!
end
def to_utf8( range )
utf8_ranges( range ).map do |r|
begin_enc = to_utf8_enc(r.begin)
end_enc = to_utf8_enc(r.end)
build_range begin_enc, end_enc
end.flatten!
end
##
# Perform a 3-way comparison of the number of codepoints advertised by
# the unicode spec for the given range, the originally parsed range,
# and the resulting utf8 encoded range.
def count_codepoints( code )
code.split(' ').inject(1) do |acc, elt|
if elt =~ /0x(.+)\.\.0x(.+)/
if @encoding == :utf8
acc * (from_utf8_enc($2) - from_utf8_enc($1) + 1)
else
acc * ($2.hex - $1.hex + 1)
end
else
acc
end
end
end
def is_valid?( range, desc, codes )
spec_count = 1
spec_count = $1.to_i if desc =~ /\[(\d+)\]/
range_count = range.end - range.begin + 1
sum = codes.inject(0) { |acc, elt| acc + count_codepoints(elt) }
sum == spec_count and sum == range_count
end
##
# Generate the state maching to stdout
def generate_machine( name, property )
pipe = " "
@output.puts " #{name} = "
each_alpha( @chart_url, property ) do |range, desc|
codes = (@encoding == :ucs4) ? to_ucs4(range) : to_utf8(range)
#raise "Invalid encoding of range #{range}: #{codes.inspect}" unless
# is_valid? range, desc, codes
range_width = codes.map { |a| a.size }.max
range_width = RANGE_WIDTH if range_width < RANGE_WIDTH
desc_width = TOTAL_WIDTH - RANGE_WIDTH - 11
desc_width -= (range_width - RANGE_WIDTH) if range_width > RANGE_WIDTH
if desc.size > desc_width
desc = desc[0..desc_width - 4] + "..."
end
codes.each_with_index do |r, idx|
desc = "" unless idx.zero?
code = "%-#{range_width}s" % r
@output.puts " #{pipe} #{code} ##{desc}"
pipe = "|"
end
end
@output.puts " ;"
@output.puts ""
end
@output.puts <<EOF
# The following Ragel file was autogenerated with #{$0}
# from: #{@chart_url}
#
# It defines #{properties}.
#
# To use this, make sure that your alphtype is set to #{ALPHTYPES[@encoding]},
# and that your input is in #{@encoding}.
%%{
machine #{machine_name};
EOF
properties.each { |x| generate_machine( x, x ) }
@output.puts <<EOF
}%%
EOF

View File

@ -0,0 +1,19 @@
package textseg
import "unicode/utf8"
// ScanGraphemeClusters is a split function for bufio.Scanner that splits
// on UTF8 sequence boundaries.
//
// This is included largely for completeness, since this behavior is already
// built in to Go when ranging over a string.
func ScanUTF8Sequences(data []byte, atEOF bool) (int, []byte, error) {
if len(data) == 0 {
return 0, nil, nil
}
r, seqLen := utf8.DecodeRune(data)
if r == utf8.RuneError && !atEOF {
return 0, nil, nil
}
return seqLen, data[:seqLen], nil
}