miloignis/kraken
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Remove old parsing

Browse Source
This commit is contained in:
Nathan Braswell
2020-03-29 20:49:50 -04:00
parent ce7d228358
commit f86a6a600b
1 changed files with 1 additions and 225 deletions
Download Patch File Download Diff File Expand all files Collapse all files

226
k_prime.krak
View File

@@ -7,122 +7,6 @@ import map:*
import fungll:*
fun tokenize(s: str): vec<str> {
var to_ret = vec<str>()
for (var i = 0; i < s.length(); i++;) {
if (s[i] == ' ' || s[i] == '\t' || s[i] == ',' || s[i] == '\n') {
i++
while (i < s.length() && (s[i] == ' ' || s[i] == '\t' || s[i] == ',' || s[i] == '\n')) {
i++;
}
i--
} else if (i+1 < s.length() && s[i] == '~' && s[i+1] == '@') {
to_ret.add(str("~@"))
i++
} else if ( s[i] == '[' || s[i] == ']' || s[i] == '{' || s[i] == '}' || s[i] == '(' || s[i] == ')' || s[i] == '\'' || s[i] == '`' || s[i] == '~' || s[i] == '^' || s[i] == '@') { // '
to_ret.add(str(s[i]))
} else if (s[i] == ';') {
var next_tok = str(s[i])
i++
while (i < s.length() && (s[i] != '\n')) {
next_tok += s[i]
i++
}
i--
} else if (s[i] == '"') {
var str_start = i
var next_tok = str(s[i])
i++
while (i < s.length()) {
next_tok += s[i]
if s[i] == '"' {
var backslash_count = 0
while ((i-backslash_count)-1 > str_start && s[(i-backslash_count)-1] == '\\') {
backslash_count++
}
// even number of backslashes
if (backslash_count & 1) == 0 {
break
}
}
i++
}
to_ret.add(next_tok)
} else {
var next_tok = str(s[i])
i++
while (i < s.length() && !( s[i] == ' ' || s[i] == '\t' || s[i] == ',' || s[i] == '\n' || s[i] == '[' || s[i] == ']' || s[i] == '{' || s[i] == '}' || s[i] == '(' || s[i] == ')' || s[i] == '\'' || s[i] == '`' || s[i] == '~' || s[i] == '^' || s[i] == '@' || s[i] == ';')) { // '
next_tok += s[i]
i++
}
to_ret.add(next_tok)
i--
}
}
return to_ret
}
fun read_form(tokens: *vec<str>, i: *int): MalResult {
if ((*tokens)[*i] == "(" || (*tokens)[*i] == "[") {
return read_list(tokens, i, (*tokens)[*i] == "[")
} else if ((*tokens)[*i] == "{") {
return read_dict(tokens, i)
} else if ((*tokens)[*i] == "@") {
(*i)++;
var inner = read_form(tokens, i)
if (is_err(inner)) {
return inner
}
return MalResult::Ok(MalValue::List(vec(MalValue::Symbol(str("deref")), get_value(inner))))
} else if ((*tokens)[*i] == "'") {
(*i)++;
var inner = read_form(tokens, i)
if (is_err(inner)) {
return inner
}
return MalResult::Ok(MalValue::List(vec(MalValue::Symbol(str("quote")), get_value(inner))))
} else if ((*tokens)[*i] == "`") {
(*i)++;
var inner = read_form(tokens, i)
if (is_err(inner)) {
return inner
}
return MalResult::Ok(MalValue::List(vec(MalValue::Symbol(str("quasiquote")), get_value(inner))))
} else if ((*tokens)[*i] == "~") {
(*i)++;
var inner = read_form(tokens, i)
if (is_err(inner)) {
return inner
}
return MalResult::Ok(MalValue::List(vec(MalValue::Symbol(str("unquote")), get_value(inner))))
} else if ((*tokens)[*i] == "~@") {
(*i)++;
var inner = read_form(tokens, i)
if (is_err(inner)) {
return inner
}
return MalResult::Ok(MalValue::List(vec(MalValue::Symbol(str("splice-unquote")), get_value(inner))))
} else {
return read_atom(tokens, i)
}
}
fun read_dict(tokens: *vec<str>, i: *int): MalResult {
(*i)++;
var values = vec<MalValue>()
while (*i < tokens->size && (*tokens)[*i] != "}") {
var result = read_form(tokens, i)
if (is_err(result)) {
return result
}
values.add(get_value(result))
}
if (*i == tokens->size) {
return MalResult::Err(MalValue::String(str("unbalanced {")))
}
(*i)++;
return create_map(values)
}
fun create_map(values: vec<MalValue>): MalResult {
var to_ret = map<MalValue,MalValue>()
if values.size & 1 == 1 {
@@ -155,82 +39,7 @@ fun get_map(m: MalValue): map<MalValue, MalValue> {
}
error("can't get_map not a map")
}
fun read_list(tokens: *vec<str>, i: *int, is_vec: bool): MalResult {
var to_ret = vec<MalValue>()
(*i)++;
while (*i < tokens->size && ((!is_vec &&(*tokens)[*i] != ")") || (is_vec &&(*tokens)[*i] != "]"))) {
var result = read_form(tokens, i)
if (is_err(result)) {
return result
}
to_ret.add(get_value(result))
}
if (*i == tokens->size) {
if is_vec {
return MalResult::Err(MalValue::String(str("unbalanced [")))
} else {
return MalResult::Err(MalValue::String(str("unbalanced (")))
}
}
(*i)++;
if is_vec {
return MalResult::Ok(MalValue::Vector(to_ret))
} else {
return MalResult::Ok(MalValue::List(to_ret))
}
}
fun read_atom(tokens: *vec<str>, i: *int): MalResult {
var all_num = true
var token = (*tokens)[*i]
(*i)++
for (var j = 0; j < token.length(); j++;) {
all_num = all_num && ((j == 0 && token[j] == '-' && token.length() > 1) || token[j] >= '0' && token[j] <= '9')
}
if (all_num) {
return MalResult::Ok(MalValue::Int(string_to_num<int>(token)))
} else if (token == "true") {
return MalResult::Ok(MalValue::True())
} else if (token == "false") {
return MalResult::Ok(MalValue::False())
} else if (token == "nil") {
return MalResult::Ok(MalValue::Nil())
} else if (token[0] == '"') {
var to_ret = str()
if token.length() == 1 || token[token.length()-1] != '"' {
return MalResult::Err(MalValue::String(str("unbalanced \""))) //"
}
for (var i = 1; i < token.length()-1; i++;) {
if token[i] == '\\' {
if i == token.length()-2 {
return MalResult::Err(MalValue::String(str("unbalanced \""))) //"
}
if token[i+1] == 'n' {
to_ret += '\n'
} else if token[i+1] == '\\' || token[i+1] == '"' {
to_ret += token[i+1]
} else {
return MalResult::Err(MalValue::String(str("bad string escape")))
}
// skip
i++
} else {
to_ret += token[i]
}
}
return MalResult::Ok(MalValue::String(to_ret))
} else if (token[0] == ':') {
return MalResult::Ok(MalValue::Keyword(token.slice(1,-1)))
} else {
return MalResult::Ok(MalValue::Symbol(token))
}
}
fun read_str(grammer: ref Grammer<MalResult>, s: str): MalResult {
var tokens = tokenize(s)
var normal_to_ret = MalResult::Ok(MalValue::Nil())
var new_to_ret = MalResult::Ok(MalValue::Nil())
var BSR = fungll(grammer, s)
var success = false
for (var i = 0; i < BSR.data.size; i++;) {
@@ -238,13 +47,7 @@ fun read_str(grammer: ref Grammer<MalResult>, s: str): MalResult {
success = success || (BSR.data[i].nonterminal == grammer.start_symbol && BSR.data[i].right == s.length())
}
if success {
/*println("parsed: " + s)*/
/*println(str("length of BSR is: ") + BSR.size())*/
/*for (var i = 0; i < BSR.data.size; i++;) {*/
/*var BS = BSR.data[i]*/
/*println(str() + i + ": " + grammer.to_string(BSR.data[i]))*/
/*}*/
new_to_ret = grammer.eval_BSR(s, BSR)
return grammer.eval_BSR(s, BSR)
} else {
println("trying to parse: " + s)
println(str("length of BSR is: ") + BSR.size())
@@ -255,33 +58,6 @@ fun read_str(grammer: ref Grammer<MalResult>, s: str): MalResult {
println("Parse failed")
error("faileD")
}
// comment, print nothing
if tokens.size == 0 {
normal_to_ret = MalResult::Err(MalValue::String(str("")))
} else {
var i = 0
normal_to_ret = read_form(&tokens, &i)
}
/*var readably = false*/
var readably = true
if is_err(normal_to_ret) {
println("normal Was error")
println(pr_str(get_err(normal_to_ret), readably))
} else {
println("normal Was value")
println(pr_str(get_value(normal_to_ret), readably))
}
if is_err(new_to_ret) {
println("new Was error")
println(pr_str(get_err(new_to_ret), readably))
} else {
println("new Was value")
println(pr_str(get_value(new_to_ret), readably))
}
/*return normal_to_ret*/
return new_to_ret
}
adt MalValue {
Nil,