Last active
May 25, 2019 20:51
-
-
Save marihachi/89ee7308fae2600ed979b9416dc878f8 to your computer and use it in GitHub Desktop.
A csv parser written by PEG.js
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/* | |
* Generated by PEG.js 0.10.0. | |
* | |
* http://pegjs.org/ | |
*/ | |
"use strict"; | |
function peg$subclass(child, parent) { | |
function ctor() { this.constructor = child; } | |
ctor.prototype = parent.prototype; | |
child.prototype = new ctor(); | |
} | |
function peg$SyntaxError(message, expected, found, location) { | |
this.message = message; | |
this.expected = expected; | |
this.found = found; | |
this.location = location; | |
this.name = "SyntaxError"; | |
if (typeof Error.captureStackTrace === "function") { | |
Error.captureStackTrace(this, peg$SyntaxError); | |
} | |
} | |
peg$subclass(peg$SyntaxError, Error); | |
peg$SyntaxError.buildMessage = function(expected, found) { | |
var DESCRIBE_EXPECTATION_FNS = { | |
literal: function(expectation) { | |
return "\"" + literalEscape(expectation.text) + "\""; | |
}, | |
"class": function(expectation) { | |
var escapedParts = "", | |
i; | |
for (i = 0; i < expectation.parts.length; i++) { | |
escapedParts += expectation.parts[i] instanceof Array | |
? classEscape(expectation.parts[i][0]) + "-" + classEscape(expectation.parts[i][1]) | |
: classEscape(expectation.parts[i]); | |
} | |
return "[" + (expectation.inverted ? "^" : "") + escapedParts + "]"; | |
}, | |
any: function(expectation) { | |
return "any character"; | |
}, | |
end: function(expectation) { | |
return "end of input"; | |
}, | |
other: function(expectation) { | |
return expectation.description; | |
} | |
}; | |
function hex(ch) { | |
return ch.charCodeAt(0).toString(16).toUpperCase(); | |
} | |
function literalEscape(s) { | |
return s | |
.replace(/\\/g, '\\\\') | |
.replace(/"/g, '\\"') | |
.replace(/\0/g, '\\0') | |
.replace(/\t/g, '\\t') | |
.replace(/\n/g, '\\n') | |
.replace(/\r/g, '\\r') | |
.replace(/[\x00-\x0F]/g, function(ch) { return '\\x0' + hex(ch); }) | |
.replace(/[\x10-\x1F\x7F-\x9F]/g, function(ch) { return '\\x' + hex(ch); }); | |
} | |
function classEscape(s) { | |
return s | |
.replace(/\\/g, '\\\\') | |
.replace(/\]/g, '\\]') | |
.replace(/\^/g, '\\^') | |
.replace(/-/g, '\\-') | |
.replace(/\0/g, '\\0') | |
.replace(/\t/g, '\\t') | |
.replace(/\n/g, '\\n') | |
.replace(/\r/g, '\\r') | |
.replace(/[\x00-\x0F]/g, function(ch) { return '\\x0' + hex(ch); }) | |
.replace(/[\x10-\x1F\x7F-\x9F]/g, function(ch) { return '\\x' + hex(ch); }); | |
} | |
function describeExpectation(expectation) { | |
return DESCRIBE_EXPECTATION_FNS[expectation.type](expectation); | |
} | |
function describeExpected(expected) { | |
var descriptions = new Array(expected.length), | |
i, j; | |
for (i = 0; i < expected.length; i++) { | |
descriptions[i] = describeExpectation(expected[i]); | |
} | |
descriptions.sort(); | |
if (descriptions.length > 0) { | |
for (i = 1, j = 1; i < descriptions.length; i++) { | |
if (descriptions[i - 1] !== descriptions[i]) { | |
descriptions[j] = descriptions[i]; | |
j++; | |
} | |
} | |
descriptions.length = j; | |
} | |
switch (descriptions.length) { | |
case 1: | |
return descriptions[0]; | |
case 2: | |
return descriptions[0] + " or " + descriptions[1]; | |
default: | |
return descriptions.slice(0, -1).join(", ") | |
+ ", or " | |
+ descriptions[descriptions.length - 1]; | |
} | |
} | |
function describeFound(found) { | |
return found ? "\"" + literalEscape(found) + "\"" : "end of input"; | |
} | |
return "Expected " + describeExpected(expected) + " but " + describeFound(found) + " found."; | |
}; | |
function peg$parse(input, options) { | |
options = options !== void 0 ? options : {}; | |
var peg$FAILED = {}, | |
peg$startRuleFunctions = { start: peg$parsestart }, | |
peg$startRuleFunction = peg$parsestart, | |
peg$c0 = function(head, r) { return r; }, | |
peg$c1 = function(head, rs) { return [head, ...rs]; }, | |
peg$c2 = function(head, c) { return c; }, | |
peg$c3 = function(head, cs) { return [head, ...cs]; }, | |
peg$c4 = function(s) { return s; }, | |
peg$c5 = peg$anyExpectation(), | |
peg$c6 = function(c) { return c; }, | |
peg$c7 = "\n", | |
peg$c8 = peg$literalExpectation("\n", false), | |
peg$c9 = "\r\n", | |
peg$c10 = peg$literalExpectation("\r\n", false), | |
peg$c11 = "\r", | |
peg$c12 = peg$literalExpectation("\r", false), | |
peg$c13 = /^["]/, | |
peg$c14 = peg$classExpectation(["\""], false, false), | |
peg$c15 = /^[,]/, | |
peg$c16 = peg$classExpectation([","], false, false), | |
peg$currPos = 0, | |
peg$savedPos = 0, | |
peg$posDetailsCache = [{ line: 1, column: 1 }], | |
peg$maxFailPos = 0, | |
peg$maxFailExpected = [], | |
peg$silentFails = 0, | |
peg$result; | |
if ("startRule" in options) { | |
if (!(options.startRule in peg$startRuleFunctions)) { | |
throw new Error("Can't start parsing from rule \"" + options.startRule + "\"."); | |
} | |
peg$startRuleFunction = peg$startRuleFunctions[options.startRule]; | |
} | |
function text() { | |
return input.substring(peg$savedPos, peg$currPos); | |
} | |
function location() { | |
return peg$computeLocation(peg$savedPos, peg$currPos); | |
} | |
function expected(description, location) { | |
location = location !== void 0 ? location : peg$computeLocation(peg$savedPos, peg$currPos) | |
throw peg$buildStructuredError( | |
[peg$otherExpectation(description)], | |
input.substring(peg$savedPos, peg$currPos), | |
location | |
); | |
} | |
function error(message, location) { | |
location = location !== void 0 ? location : peg$computeLocation(peg$savedPos, peg$currPos) | |
throw peg$buildSimpleError(message, location); | |
} | |
function peg$literalExpectation(text, ignoreCase) { | |
return { type: "literal", text: text, ignoreCase: ignoreCase }; | |
} | |
function peg$classExpectation(parts, inverted, ignoreCase) { | |
return { type: "class", parts: parts, inverted: inverted, ignoreCase: ignoreCase }; | |
} | |
function peg$anyExpectation() { | |
return { type: "any" }; | |
} | |
function peg$endExpectation() { | |
return { type: "end" }; | |
} | |
function peg$otherExpectation(description) { | |
return { type: "other", description: description }; | |
} | |
function peg$computePosDetails(pos) { | |
var details = peg$posDetailsCache[pos], p; | |
if (details) { | |
return details; | |
} else { | |
p = pos - 1; | |
while (!peg$posDetailsCache[p]) { | |
p--; | |
} | |
details = peg$posDetailsCache[p]; | |
details = { | |
line: details.line, | |
column: details.column | |
}; | |
while (p < pos) { | |
if (input.charCodeAt(p) === 10) { | |
details.line++; | |
details.column = 1; | |
} else { | |
details.column++; | |
} | |
p++; | |
} | |
peg$posDetailsCache[pos] = details; | |
return details; | |
} | |
} | |
function peg$computeLocation(startPos, endPos) { | |
var startPosDetails = peg$computePosDetails(startPos), | |
endPosDetails = peg$computePosDetails(endPos); | |
return { | |
start: { | |
offset: startPos, | |
line: startPosDetails.line, | |
column: startPosDetails.column | |
}, | |
end: { | |
offset: endPos, | |
line: endPosDetails.line, | |
column: endPosDetails.column | |
} | |
}; | |
} | |
function peg$fail(expected) { | |
if (peg$currPos < peg$maxFailPos) { return; } | |
if (peg$currPos > peg$maxFailPos) { | |
peg$maxFailPos = peg$currPos; | |
peg$maxFailExpected = []; | |
} | |
peg$maxFailExpected.push(expected); | |
} | |
function peg$buildSimpleError(message, location) { | |
return new peg$SyntaxError(message, null, null, location); | |
} | |
function peg$buildStructuredError(expected, found, location) { | |
return new peg$SyntaxError( | |
peg$SyntaxError.buildMessage(expected, found), | |
expected, | |
found, | |
location | |
); | |
} | |
function peg$parsestart() { | |
var s0; | |
s0 = peg$parserecodes(); | |
return s0; | |
} | |
function peg$parserecodes() { | |
var s0, s1, s2, s3, s4, s5; | |
s0 = peg$currPos; | |
s1 = peg$parserecode(); | |
if (s1 !== peg$FAILED) { | |
s2 = []; | |
s3 = peg$currPos; | |
s4 = peg$parselineBreak(); | |
if (s4 !== peg$FAILED) { | |
s5 = peg$parserecode(); | |
if (s5 !== peg$FAILED) { | |
peg$savedPos = s3; | |
s4 = peg$c0(s1, s5); | |
s3 = s4; | |
} else { | |
peg$currPos = s3; | |
s3 = peg$FAILED; | |
} | |
} else { | |
peg$currPos = s3; | |
s3 = peg$FAILED; | |
} | |
while (s3 !== peg$FAILED) { | |
s2.push(s3); | |
s3 = peg$currPos; | |
s4 = peg$parselineBreak(); | |
if (s4 !== peg$FAILED) { | |
s5 = peg$parserecode(); | |
if (s5 !== peg$FAILED) { | |
peg$savedPos = s3; | |
s4 = peg$c0(s1, s5); | |
s3 = s4; | |
} else { | |
peg$currPos = s3; | |
s3 = peg$FAILED; | |
} | |
} else { | |
peg$currPos = s3; | |
s3 = peg$FAILED; | |
} | |
} | |
if (s2 !== peg$FAILED) { | |
peg$savedPos = s0; | |
s1 = peg$c1(s1, s2); | |
s0 = s1; | |
} else { | |
peg$currPos = s0; | |
s0 = peg$FAILED; | |
} | |
} else { | |
peg$currPos = s0; | |
s0 = peg$FAILED; | |
} | |
return s0; | |
} | |
function peg$parserecode() { | |
var s0, s1, s2, s3, s4, s5; | |
s0 = peg$currPos; | |
s1 = peg$parsecell(); | |
if (s1 !== peg$FAILED) { | |
s2 = []; | |
s3 = peg$currPos; | |
s4 = peg$parsecomma(); | |
if (s4 !== peg$FAILED) { | |
s5 = peg$parsecell(); | |
if (s5 !== peg$FAILED) { | |
peg$savedPos = s3; | |
s4 = peg$c2(s1, s5); | |
s3 = s4; | |
} else { | |
peg$currPos = s3; | |
s3 = peg$FAILED; | |
} | |
} else { | |
peg$currPos = s3; | |
s3 = peg$FAILED; | |
} | |
while (s3 !== peg$FAILED) { | |
s2.push(s3); | |
s3 = peg$currPos; | |
s4 = peg$parsecomma(); | |
if (s4 !== peg$FAILED) { | |
s5 = peg$parsecell(); | |
if (s5 !== peg$FAILED) { | |
peg$savedPos = s3; | |
s4 = peg$c2(s1, s5); | |
s3 = s4; | |
} else { | |
peg$currPos = s3; | |
s3 = peg$FAILED; | |
} | |
} else { | |
peg$currPos = s3; | |
s3 = peg$FAILED; | |
} | |
} | |
if (s2 !== peg$FAILED) { | |
peg$savedPos = s0; | |
s1 = peg$c3(s1, s2); | |
s0 = s1; | |
} else { | |
peg$currPos = s0; | |
s0 = peg$FAILED; | |
} | |
} else { | |
peg$currPos = s0; | |
s0 = peg$FAILED; | |
} | |
return s0; | |
} | |
function peg$parsecell() { | |
var s0, s1, s2, s3, s4; | |
s0 = peg$currPos; | |
s1 = peg$parsequotation(); | |
if (s1 !== peg$FAILED) { | |
s2 = peg$currPos; | |
s3 = []; | |
s4 = peg$parsequotedChar(); | |
while (s4 !== peg$FAILED) { | |
s3.push(s4); | |
s4 = peg$parsequotedChar(); | |
} | |
if (s3 !== peg$FAILED) { | |
s2 = input.substring(s2, peg$currPos); | |
} else { | |
s2 = s3; | |
} | |
if (s2 !== peg$FAILED) { | |
s3 = peg$parsequotation(); | |
if (s3 !== peg$FAILED) { | |
peg$savedPos = s0; | |
s1 = peg$c4(s2); | |
s0 = s1; | |
} else { | |
peg$currPos = s0; | |
s0 = peg$FAILED; | |
} | |
} else { | |
peg$currPos = s0; | |
s0 = peg$FAILED; | |
} | |
} else { | |
peg$currPos = s0; | |
s0 = peg$FAILED; | |
} | |
if (s0 === peg$FAILED) { | |
s0 = peg$currPos; | |
s1 = peg$currPos; | |
s2 = []; | |
s3 = peg$parsechar(); | |
while (s3 !== peg$FAILED) { | |
s2.push(s3); | |
s3 = peg$parsechar(); | |
} | |
if (s2 !== peg$FAILED) { | |
s1 = input.substring(s1, peg$currPos); | |
} else { | |
s1 = s2; | |
} | |
if (s1 !== peg$FAILED) { | |
peg$savedPos = s0; | |
s1 = peg$c4(s1); | |
} | |
s0 = s1; | |
} | |
return s0; | |
} | |
function peg$parsequotedChar() { | |
var s0, s1, s2; | |
s0 = peg$currPos; | |
s1 = peg$currPos; | |
peg$silentFails++; | |
s2 = peg$parsequotation(); | |
peg$silentFails--; | |
if (s2 === peg$FAILED) { | |
s1 = void 0; | |
} else { | |
peg$currPos = s1; | |
s1 = peg$FAILED; | |
} | |
if (s1 !== peg$FAILED) { | |
if (input.length > peg$currPos) { | |
s2 = input.charAt(peg$currPos); | |
peg$currPos++; | |
} else { | |
s2 = peg$FAILED; | |
if (peg$silentFails === 0) { peg$fail(peg$c5); } | |
} | |
if (s2 !== peg$FAILED) { | |
peg$savedPos = s0; | |
s1 = peg$c6(s2); | |
s0 = s1; | |
} else { | |
peg$currPos = s0; | |
s0 = peg$FAILED; | |
} | |
} else { | |
peg$currPos = s0; | |
s0 = peg$FAILED; | |
} | |
return s0; | |
} | |
function peg$parsechar() { | |
var s0, s1, s2; | |
s0 = peg$currPos; | |
s1 = peg$currPos; | |
peg$silentFails++; | |
s2 = peg$parsecomma(); | |
if (s2 === peg$FAILED) { | |
s2 = peg$parsequotation(); | |
if (s2 === peg$FAILED) { | |
s2 = peg$parselineBreak(); | |
} | |
} | |
peg$silentFails--; | |
if (s2 === peg$FAILED) { | |
s1 = void 0; | |
} else { | |
peg$currPos = s1; | |
s1 = peg$FAILED; | |
} | |
if (s1 !== peg$FAILED) { | |
if (input.length > peg$currPos) { | |
s2 = input.charAt(peg$currPos); | |
peg$currPos++; | |
} else { | |
s2 = peg$FAILED; | |
if (peg$silentFails === 0) { peg$fail(peg$c5); } | |
} | |
if (s2 !== peg$FAILED) { | |
peg$savedPos = s0; | |
s1 = peg$c6(s2); | |
s0 = s1; | |
} else { | |
peg$currPos = s0; | |
s0 = peg$FAILED; | |
} | |
} else { | |
peg$currPos = s0; | |
s0 = peg$FAILED; | |
} | |
return s0; | |
} | |
function peg$parselineBreak() { | |
var s0; | |
if (input.charCodeAt(peg$currPos) === 10) { | |
s0 = peg$c7; | |
peg$currPos++; | |
} else { | |
s0 = peg$FAILED; | |
if (peg$silentFails === 0) { peg$fail(peg$c8); } | |
} | |
if (s0 === peg$FAILED) { | |
if (input.substr(peg$currPos, 2) === peg$c9) { | |
s0 = peg$c9; | |
peg$currPos += 2; | |
} else { | |
s0 = peg$FAILED; | |
if (peg$silentFails === 0) { peg$fail(peg$c10); } | |
} | |
if (s0 === peg$FAILED) { | |
if (input.charCodeAt(peg$currPos) === 13) { | |
s0 = peg$c11; | |
peg$currPos++; | |
} else { | |
s0 = peg$FAILED; | |
if (peg$silentFails === 0) { peg$fail(peg$c12); } | |
} | |
} | |
} | |
return s0; | |
} | |
function peg$parsequotation() { | |
var s0; | |
if (peg$c13.test(input.charAt(peg$currPos))) { | |
s0 = input.charAt(peg$currPos); | |
peg$currPos++; | |
} else { | |
s0 = peg$FAILED; | |
if (peg$silentFails === 0) { peg$fail(peg$c14); } | |
} | |
return s0; | |
} | |
function peg$parsecomma() { | |
var s0; | |
if (peg$c15.test(input.charAt(peg$currPos))) { | |
s0 = input.charAt(peg$currPos); | |
peg$currPos++; | |
} else { | |
s0 = peg$FAILED; | |
if (peg$silentFails === 0) { peg$fail(peg$c16); } | |
} | |
return s0; | |
} | |
peg$result = peg$startRuleFunction(); | |
if (peg$result !== peg$FAILED && peg$currPos === input.length) { | |
return peg$result; | |
} else { | |
if (peg$result !== peg$FAILED && peg$currPos < input.length) { | |
peg$fail(peg$endExpectation()); | |
} | |
throw peg$buildStructuredError( | |
peg$maxFailExpected, | |
peg$maxFailPos < input.length ? input.charAt(peg$maxFailPos) : null, | |
peg$maxFailPos < input.length | |
? peg$computeLocation(peg$maxFailPos, peg$maxFailPos + 1) | |
: peg$computeLocation(peg$maxFailPos, peg$maxFailPos) | |
); | |
} | |
} | |
module.exports = { | |
SyntaxError: peg$SyntaxError, | |
parse: peg$parse | |
}; |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
start = recodes | |
recodes = head:recode rs:(lineBreak r:recode { return r; })* { return [head, ...rs]; } | |
recode = head:cell cs:(comma c:cell { return c; })* { return [head, ...cs]; } | |
cell | |
= quotation s:$(quotedChar*) quotation { return s; } | |
/ s:$(char*) { return s; } | |
quotedChar = !quotation c:. { return c; } | |
char = !(comma / quotation / lineBreak) c:. { return c; } | |
lineBreak = "\n" / "\r\n" / "\r" | |
quotation = ["] | |
comma = [,] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment