// BEGIN of GENERIC RULES

// insignificant whitespace, not repeated
ws = _{ " " | "\t" }
arg_ws = _{ (ws | line_continuation ~ (comment_line | empty_line)*)+ }
// a line continuation, allowing an instruction to continue onto a new line
line_continuation = _{ "\\" ~ ws* ~ NEWLINE }
comment = @{ "#" ~ (!NEWLINE ~ ANY)* }
comment_line = _{ ws* ~ comment ~ NEWLINE? }
empty_line = @{ ws* ~ NEWLINE }

meta_attr_key = ${ "name" | "version" | "precompiler" | "source" | "target" }
meta_attr_value = ${ string | char+}
meta_key_pair = @{ meta_attr_key ~ arg_ws? ~ "=" ~ arg_ws?  ~ meta_attr_value }
meta_comment = @{ "--" ~ ws* ~ (!NEWLINE ~ meta_key_pair)* }
meta_comment_line = _{ ws* ~ meta_comment ~ NEWLINE? }

commands = _{
  NEWLINE*
}

string = ${ single_quoted_string | double_quoted_string }
single_quoted_string = _{ "'" ~ single_quoted_inner ~ "'" }
single_quoted_inner  = @{ (!("'" | "\\" | "\u{0000}" | "\u{001F}") ~ ANY)* ~ (escape ~ single_quoted_inner)? }
double_quoted_string  = _{ "\"" ~ inner ~ "\"" }
inner   = @{ (!("\"" | "\\" | "\u{0000}" | "\u{001F}") ~ ANY)* ~ (escape ~ inner)? }
escape  = @{ "\\" ~ ("b" | "t" | "n" | "f" | "r" | "\"" | "\\" | "'" | unicode | NEWLINE)? }
unicode = @{ "u" ~ ASCII_HEX_DIGIT{4} | "U" ~ ASCII_HEX_DIGIT{8} }

SCRIPTS = { ADLAM | AHOM | ANATOLIAN_HIEROGLYPHS | ARABIC | ARMENIAN | AVESTAN
| BALINESE | BAMUM | BASSA_VAH | BATAK | BENGALI | BHAIKSUKI | BOPOMOFO |
BRAHMI | BRAILLE | BUGINESE | BUHID | CANADIAN_ABORIGINAL | CARIAN |
CAUCASIAN_ALBANIAN | CHAKMA | CHAM | CHEROKEE | CHORASMIAN | COPTIC |
CUNEIFORM | CYPRIOT | CYPRO_MINOAN | CYRILLIC | DESERET | DEVANAGARI |
DIVES_AKURU | DOGRA | DUPLOYAN | EGYPTIAN_HIEROGLYPHS | ELBASAN | ELYMAIC |
ETHIOPIC | GEORGIAN | GLAGOLITIC | GOTHIC | GRANTHA | GREEK | GUJARATI |
GUNJALA_GONDI | GURMUKHI | HAN | HANGUL | HANIFI_ROHINGYA | HANUNOO | HATRAN |
HEBREW | HIRAGANA | IMPERIAL_ARAMAIC | INHERITED | INSCRIPTIONAL_PAHLAVI |
INSCRIPTIONAL_PARTHIAN | JAVANESE | KAITHI | KANNADA | KATAKANA | KAWI |
KAYAH_LI | KHAROSHTHI | KHITAN_SMALL_SCRIPT | KHMER | KHOJKI | KHUDAWADI | LAO
| LATIN | LEPCHA | LIMBU | LINEAR_A | LINEAR_B | LISU | LYCIAN | LYDIAN |
MAHAJANI | MAKASAR | MALAYALAM | MANDAIC | MANICHAEAN | MARCHEN | MASARAM_GONDI
| MEDEFAIDRIN | MEETEI_MAYEK | MENDE_KIKAKUI | MEROITIC_CURSIVE |
MEROITIC_HIEROGLYPHS | MIAO | MODI | MONGOLIAN | MRO | MULTANI | MYANMAR |
NABATAEAN | NAG_MUNDARI | NANDINAGARI | NEW_TAI_LUE | NEWA | NKO | NUSHU |
NYIAKENG_PUACHUE_HMONG | OGHAM | OL_CHIKI | OLD_HUNGARIAN | OLD_ITALIC |
OLD_NORTH_ARABIAN | OLD_PERMIC | OLD_PERSIAN | OLD_SOGDIAN | OLD_SOUTH_ARABIAN
| OLD_TURKIC | OLD_UYGHUR | ORIYA | OSAGE | OSMANYA | PAHAWH_HMONG | PALMYRENE
| PAU_CIN_HAU | PHAGS_PA | PHOENICIAN | PSALTER_PAHLAVI | REJANG | RUNIC |
SAMARITAN | SAURASHTRA | SHARADA | SHAVIAN | SIDDHAM | SIGNWRITING | SINHALA |
SOGDIAN | SORA_SOMPENG | SOYOMBO | SUNDANESE | SYLOTI_NAGRI | SYRIAC | TAGALOG
| TAGBANWA | TAI_LE | TAI_THAM | TAI_VIET | TAKRI | TAMIL | TANGSA | TANGUT |
TELUGU | THAANA | THAI | TIBETAN | TIFINAGH | TIRHUTA | TOTO | UGARITIC | VAI |
VITHKUQI | WANCHO | WARANG_CITI | YEZIDI | YI | ZANABAZAR_SQUARE }
char = { LETTER | NUMBER | "." | "-" | "_" | "/" | ":" | SCRIPTS }

file = {
  SOI ~
  (empty_line | meta_comment_line | comment_line | ANY)*
  ~ EOI
}