用pegjs重写过滤逻辑

This commit is contained in:
HSunboy 2018-07-05 11:16:30 +08:00
parent 6eb8a18c48
commit 152f186a2e
10 changed files with 1099 additions and 9370 deletions

View File

@ -330,17 +330,8 @@ module.exports = (function(){
function parse_init() { function parse_init() {
var result0; var result0;
var pos0, pos1;
pos0 = pos; result0 = (function(offset) { params = []; return true; })(pos) ? "" : null;
pos1 = pos;
result0 = [];
if (result0 !== null) {
result0 = (function(offset) { params = []; return true; })(pos0);
}
if (result0 === null) {
pos = pos0;
}
return result0; return result0;
} }
@ -491,6 +482,7 @@ module.exports = (function(){
} }
if (result0 !== null) { if (result0 !== null) {
result0 = (function(offset, s) { result0 = (function(offset, s) {
console.log(s);
return s[2]; return s[2];
})(pos0, result0); })(pos0, result0);
} }
@ -2323,24 +2315,15 @@ module.exports = (function(){
function parse_expr_list_or_empty() { function parse_expr_list_or_empty() {
var result0; var result0;
var pos0, pos1;
result0 = parse_expr_list(); result0 = parse_expr_list();
if (result0 === null) { if (result0 === null) {
pos0 = pos; result0 = (function(offset, l) {
pos1 = pos;
result0 = [];
if (result0 !== null) {
result0 = (function(offset) {
return { return {
type : 'expr_list', type : 'expr_list',
value : [] value : []
} }
})(pos0); })(pos, result0) ? "" : null;
}
if (result0 === null) {
pos = pos0;
}
} }
return result0; return result0;
} }
@ -7462,17 +7445,8 @@ module.exports = (function(){
function parse_proc_init() { function parse_proc_init() {
var result0; var result0;
var pos0, pos1;
pos0 = pos; result0 = (function(offset) { varList = []; return true; })(pos) ? "" : null;
pos1 = pos;
result0 = [];
if (result0 !== null) {
result0 = (function(offset) { varList = []; return true; })(pos0);
}
if (result0 === null) {
pos = pos0;
}
return result0; return result0;
} }

997
core/comment.js Normal file
View File

@ -0,0 +1,997 @@
module.exports = (function(){
/*
* Generated by PEG.js 0.7.0.
*
* http://pegjs.majda.cz/
*/
function quote(s) {
/*
* ECMA-262, 5th ed., 7.8.4: All characters may appear literally in a
* string literal except for the closing quote character, backslash,
* carriage return, line separator, paragraph separator, and line feed.
* Any character may appear in the form of an escape sequence.
*
* For portability, we also escape escape all control and non-ASCII
* characters. Note that "\0" and "\v" escape sequences are not used
* because JSHint does not like the first and IE the second.
*/
return '"' + s
.replace(/\\/g, '\\\\') // backslash
.replace(/"/g, '\\"') // closing quote character
.replace(/\x08/g, '\\b') // backspace
.replace(/\t/g, '\\t') // horizontal tab
.replace(/\n/g, '\\n') // line feed
.replace(/\f/g, '\\f') // form feed
.replace(/\r/g, '\\r') // carriage return
.replace(/[\x00-\x07\x0B\x0E-\x1F\x80-\uFFFF]/g, escape)
+ '"';
}
var result = {
/*
* Parses the input with a generated parser. If the parsing is successfull,
* returns a value explicitly or implicitly specified by the grammar from
* which the parser was generated (see |PEG.buildParser|). If the parsing is
* unsuccessful, throws |PEG.parser.SyntaxError| describing the error.
*/
parse: function(input, startRule) {
var parseFunctions = {
"start": parse_start,
"union_stmt": parse_union_stmt,
"comment": parse_comment,
"singleLine": parse_singleLine,
"multiLine": parse_multiLine,
"quote": parse_quote,
"kw_start": parse_kw_start,
"KW_SINGLE_LINE_START": parse_KW_SINGLE_LINE_START,
"KW_SINGLE_LINE_END": parse_KW_SINGLE_LINE_END,
"KW_MULTI_LINE_START": parse_KW_MULTI_LINE_START,
"KW_MULTI_LINE_END": parse_KW_MULTI_LINE_END,
"__": parse___,
"whitespace": parse_whitespace
};
if (startRule !== undefined) {
if (parseFunctions[startRule] === undefined) {
throw new Error("Invalid rule name: " + quote(startRule) + ".");
}
} else {
startRule = "start";
}
var pos = 0;
var reportFailures = 0;
var rightmostFailuresPos = 0;
var rightmostFailuresExpected = [];
function padLeft(input, padding, length) {
var result = input;
var padLength = length - input.length;
for (var i = 0; i < padLength; i++) {
result = padding + result;
}
return result;
}
function escape(ch) {
var charCode = ch.charCodeAt(0);
var escapeChar;
var length;
if (charCode <= 0xFF) {
escapeChar = 'x';
length = 2;
} else {
escapeChar = 'u';
length = 4;
}
return '\\' + escapeChar + padLeft(charCode.toString(16).toUpperCase(), '0', length);
}
function matchFailed(failure) {
if (pos < rightmostFailuresPos) {
return;
}
if (pos > rightmostFailuresPos) {
rightmostFailuresPos = pos;
rightmostFailuresExpected = [];
}
rightmostFailuresExpected.push(failure);
}
function parse_start() {
var result0;
var pos0;
pos0 = pos;
result0 = parse_union_stmt();
if (result0 !== null) {
result0 = (function(offset, union_stmt) {
return union_stmt;
})(pos0, result0);
}
if (result0 === null) {
pos = pos0;
}
return result0;
}
function parse_union_stmt() {
var result0, result1, result2, result3;
var pos0, pos1, pos2, pos3, pos4, pos5, pos6;
pos0 = pos;
pos1 = pos;
result0 = [];
pos2 = pos;
pos3 = pos;
result1 = [];
pos4 = pos;
pos5 = pos;
pos6 = pos;
reportFailures++;
result2 = parse_kw_start();
reportFailures--;
if (result2 === null) {
result2 = "";
} else {
result2 = null;
pos = pos6;
}
if (result2 !== null) {
if (input.length > pos) {
result3 = input.charAt(pos);
pos++;
} else {
result3 = null;
if (reportFailures === 0) {
matchFailed("any character");
}
}
if (result3 !== null) {
result2 = [result2, result3];
} else {
result2 = null;
pos = pos5;
}
} else {
result2 = null;
pos = pos5;
}
if (result2 !== null) {
result2 = (function(offset, word) {return word})(pos4, result2[1]);
}
if (result2 === null) {
pos = pos4;
}
while (result2 !== null) {
result1.push(result2);
pos4 = pos;
pos5 = pos;
pos6 = pos;
reportFailures++;
result2 = parse_kw_start();
reportFailures--;
if (result2 === null) {
result2 = "";
} else {
result2 = null;
pos = pos6;
}
if (result2 !== null) {
if (input.length > pos) {
result3 = input.charAt(pos);
pos++;
} else {
result3 = null;
if (reportFailures === 0) {
matchFailed("any character");
}
}
if (result3 !== null) {
result2 = [result2, result3];
} else {
result2 = null;
pos = pos5;
}
} else {
result2 = null;
pos = pos5;
}
if (result2 !== null) {
result2 = (function(offset, word) {return word})(pos4, result2[1]);
}
if (result2 === null) {
pos = pos4;
}
}
if (result1 !== null) {
pos4 = pos;
result2 = parse_comment();
if (result2 !== null) {
result2 = (function(offset, comment) {return ''})(pos4, result2);
}
if (result2 === null) {
pos = pos4;
}
if (result2 === null) {
pos4 = pos;
result2 = parse_quote();
if (result2 !== null) {
result2 = (function(offset, quote) {return quote})(pos4, result2);
}
if (result2 === null) {
pos = pos4;
}
}
if (result2 !== null) {
result1 = [result1, result2];
} else {
result1 = null;
pos = pos3;
}
} else {
result1 = null;
pos = pos3;
}
if (result1 !== null) {
result1 = (function(offset, words, stmt) {return words.join("")+stmt})(pos2, result1[0], result1[1]);
}
if (result1 === null) {
pos = pos2;
}
while (result1 !== null) {
result0.push(result1);
pos2 = pos;
pos3 = pos;
result1 = [];
pos4 = pos;
pos5 = pos;
pos6 = pos;
reportFailures++;
result2 = parse_kw_start();
reportFailures--;
if (result2 === null) {
result2 = "";
} else {
result2 = null;
pos = pos6;
}
if (result2 !== null) {
if (input.length > pos) {
result3 = input.charAt(pos);
pos++;
} else {
result3 = null;
if (reportFailures === 0) {
matchFailed("any character");
}
}
if (result3 !== null) {
result2 = [result2, result3];
} else {
result2 = null;
pos = pos5;
}
} else {
result2 = null;
pos = pos5;
}
if (result2 !== null) {
result2 = (function(offset, word) {return word})(pos4, result2[1]);
}
if (result2 === null) {
pos = pos4;
}
while (result2 !== null) {
result1.push(result2);
pos4 = pos;
pos5 = pos;
pos6 = pos;
reportFailures++;
result2 = parse_kw_start();
reportFailures--;
if (result2 === null) {
result2 = "";
} else {
result2 = null;
pos = pos6;
}
if (result2 !== null) {
if (input.length > pos) {
result3 = input.charAt(pos);
pos++;
} else {
result3 = null;
if (reportFailures === 0) {
matchFailed("any character");
}
}
if (result3 !== null) {
result2 = [result2, result3];
} else {
result2 = null;
pos = pos5;
}
} else {
result2 = null;
pos = pos5;
}
if (result2 !== null) {
result2 = (function(offset, word) {return word})(pos4, result2[1]);
}
if (result2 === null) {
pos = pos4;
}
}
if (result1 !== null) {
pos4 = pos;
result2 = parse_comment();
if (result2 !== null) {
result2 = (function(offset, comment) {return ''})(pos4, result2);
}
if (result2 === null) {
pos = pos4;
}
if (result2 === null) {
pos4 = pos;
result2 = parse_quote();
if (result2 !== null) {
result2 = (function(offset, quote) {return quote})(pos4, result2);
}
if (result2 === null) {
pos = pos4;
}
}
if (result2 !== null) {
result1 = [result1, result2];
} else {
result1 = null;
pos = pos3;
}
} else {
result1 = null;
pos = pos3;
}
if (result1 !== null) {
result1 = (function(offset, words, stmt) {return words.join("")+stmt})(pos2, result1[0], result1[1]);
}
if (result1 === null) {
pos = pos2;
}
}
if (result0 !== null) {
result1 = [];
if (input.length > pos) {
result2 = input.charAt(pos);
pos++;
} else {
result2 = null;
if (reportFailures === 0) {
matchFailed("any character");
}
}
while (result2 !== null) {
result1.push(result2);
if (input.length > pos) {
result2 = input.charAt(pos);
pos++;
} else {
result2 = null;
if (reportFailures === 0) {
matchFailed("any character");
}
}
}
if (result1 !== null) {
result0 = [result0, result1];
} else {
result0 = null;
pos = pos1;
}
} else {
result0 = null;
pos = pos1;
}
if (result0 !== null) {
result0 = (function(offset, stmt, other) {return stmt.join("")+other.join("")})(pos0, result0[0], result0[1]);
}
if (result0 === null) {
pos = pos0;
}
return result0;
}
function parse_comment() {
var result0;
var pos0;
pos0 = pos;
result0 = parse_multiLine();
if (result0 === null) {
result0 = parse_singleLine();
}
if (result0 !== null) {
result0 = (function(offset, comment) {
return comment;
})(pos0, result0);
}
if (result0 === null) {
pos = pos0;
}
return result0;
}
function parse_singleLine() {
var result0, result1, result2;
var pos0, pos1;
pos0 = pos;
pos1 = pos;
result0 = parse_KW_SINGLE_LINE_START();
if (result0 !== null) {
result1 = [];
if (/^[^\r\n]/.test(input.charAt(pos))) {
result2 = input.charAt(pos);
pos++;
} else {
result2 = null;
if (reportFailures === 0) {
matchFailed("[^\\r\\n]");
}
}
while (result2 !== null) {
result1.push(result2);
if (/^[^\r\n]/.test(input.charAt(pos))) {
result2 = input.charAt(pos);
pos++;
} else {
result2 = null;
if (reportFailures === 0) {
matchFailed("[^\\r\\n]");
}
}
}
if (result1 !== null) {
result0 = [result0, result1];
} else {
result0 = null;
pos = pos1;
}
} else {
result0 = null;
pos = pos1;
}
if (result0 !== null) {
result0 = (function(offset, start, words) {
return start+words.join("")
})(pos0, result0[0], result0[1]);
}
if (result0 === null) {
pos = pos0;
}
return result0;
}
function parse_multiLine() {
var result0, result1, result2, result3;
var pos0, pos1, pos2, pos3, pos4;
pos0 = pos;
pos1 = pos;
result0 = parse_KW_MULTI_LINE_START();
if (result0 !== null) {
result1 = [];
pos2 = pos;
pos3 = pos;
pos4 = pos;
reportFailures++;
if (input.substr(pos, 2) === "*/") {
result2 = "*/";
pos += 2;
} else {
result2 = null;
if (reportFailures === 0) {
matchFailed("\"*/\"");
}
}
reportFailures--;
if (result2 === null) {
result2 = "";
} else {
result2 = null;
pos = pos4;
}
if (result2 !== null) {
if (input.length > pos) {
result3 = input.charAt(pos);
pos++;
} else {
result3 = null;
if (reportFailures === 0) {
matchFailed("any character");
}
}
if (result3 !== null) {
result2 = [result2, result3];
} else {
result2 = null;
pos = pos3;
}
} else {
result2 = null;
pos = pos3;
}
if (result2 !== null) {
result2 = (function(offset, word) {return word })(pos2, result2[1]);
}
if (result2 === null) {
pos = pos2;
}
while (result2 !== null) {
result1.push(result2);
pos2 = pos;
pos3 = pos;
pos4 = pos;
reportFailures++;
if (input.substr(pos, 2) === "*/") {
result2 = "*/";
pos += 2;
} else {
result2 = null;
if (reportFailures === 0) {
matchFailed("\"*/\"");
}
}
reportFailures--;
if (result2 === null) {
result2 = "";
} else {
result2 = null;
pos = pos4;
}
if (result2 !== null) {
if (input.length > pos) {
result3 = input.charAt(pos);
pos++;
} else {
result3 = null;
if (reportFailures === 0) {
matchFailed("any character");
}
}
if (result3 !== null) {
result2 = [result2, result3];
} else {
result2 = null;
pos = pos3;
}
} else {
result2 = null;
pos = pos3;
}
if (result2 !== null) {
result2 = (function(offset, word) {return word })(pos2, result2[1]);
}
if (result2 === null) {
pos = pos2;
}
}
if (result1 !== null) {
result2 = parse_KW_MULTI_LINE_END();
if (result2 !== null) {
result0 = [result0, result1, result2];
} else {
result0 = null;
pos = pos1;
}
} else {
result0 = null;
pos = pos1;
}
} else {
result0 = null;
pos = pos1;
}
if (result0 !== null) {
result0 = (function(offset, start, words, end) {return start+words.join("")+end })(pos0, result0[0], result0[1], result0[2]);
}
if (result0 === null) {
pos = pos0;
}
return result0;
}
function parse_quote() {
var result0, result1, result2;
var pos0, pos1;
pos0 = pos;
pos1 = pos;
if (input.charCodeAt(pos) === 34) {
result0 = "\"";
pos++;
} else {
result0 = null;
if (reportFailures === 0) {
matchFailed("\"\\\"\"");
}
}
if (result0 !== null) {
result1 = [];
if (/^[^"]/.test(input.charAt(pos))) {
result2 = input.charAt(pos);
pos++;
} else {
result2 = null;
if (reportFailures === 0) {
matchFailed("[^\"]");
}
}
while (result2 !== null) {
result1.push(result2);
if (/^[^"]/.test(input.charAt(pos))) {
result2 = input.charAt(pos);
pos++;
} else {
result2 = null;
if (reportFailures === 0) {
matchFailed("[^\"]");
}
}
}
if (result1 !== null) {
if (input.charCodeAt(pos) === 34) {
result2 = "\"";
pos++;
} else {
result2 = null;
if (reportFailures === 0) {
matchFailed("\"\\\"\"");
}
}
if (result2 !== null) {
result0 = [result0, result1, result2];
} else {
result0 = null;
pos = pos1;
}
} else {
result0 = null;
pos = pos1;
}
} else {
result0 = null;
pos = pos1;
}
if (result0 !== null) {
result0 = (function(offset, start, words, end) {return start+words.join("")+end;})(pos0, result0[0], result0[1], result0[2]);
}
if (result0 === null) {
pos = pos0;
}
if (result0 === null) {
pos0 = pos;
pos1 = pos;
if (input.charCodeAt(pos) === 39) {
result0 = "'";
pos++;
} else {
result0 = null;
if (reportFailures === 0) {
matchFailed("\"'\"");
}
}
if (result0 !== null) {
result1 = [];
if (/^[^']/.test(input.charAt(pos))) {
result2 = input.charAt(pos);
pos++;
} else {
result2 = null;
if (reportFailures === 0) {
matchFailed("[^']");
}
}
while (result2 !== null) {
result1.push(result2);
if (/^[^']/.test(input.charAt(pos))) {
result2 = input.charAt(pos);
pos++;
} else {
result2 = null;
if (reportFailures === 0) {
matchFailed("[^']");
}
}
}
if (result1 !== null) {
if (input.charCodeAt(pos) === 39) {
result2 = "'";
pos++;
} else {
result2 = null;
if (reportFailures === 0) {
matchFailed("\"'\"");
}
}
if (result2 !== null) {
result0 = [result0, result1, result2];
} else {
result0 = null;
pos = pos1;
}
} else {
result0 = null;
pos = pos1;
}
} else {
result0 = null;
pos = pos1;
}
if (result0 !== null) {
result0 = (function(offset, start, words, end) {return start+words.join("")+end;})(pos0, result0[0], result0[1], result0[2]);
}
if (result0 === null) {
pos = pos0;
}
}
return result0;
}
function parse_kw_start() {
var result0;
result0 = parse_KW_SINGLE_LINE_START();
if (result0 === null) {
result0 = parse_KW_MULTI_LINE_START();
if (result0 === null) {
if (input.charCodeAt(pos) === 34) {
result0 = "\"";
pos++;
} else {
result0 = null;
if (reportFailures === 0) {
matchFailed("\"\\\"\"");
}
}
if (result0 === null) {
if (input.charCodeAt(pos) === 39) {
result0 = "'";
pos++;
} else {
result0 = null;
if (reportFailures === 0) {
matchFailed("\"'\"");
}
}
}
}
}
return result0;
}
function parse_KW_SINGLE_LINE_START() {
var result0;
if (input.substr(pos, 2) === "--") {
result0 = "--";
pos += 2;
} else {
result0 = null;
if (reportFailures === 0) {
matchFailed("\"--\"");
}
}
return result0;
}
function parse_KW_SINGLE_LINE_END() {
var result0;
if (/^[\r\n]/.test(input.charAt(pos))) {
result0 = input.charAt(pos);
pos++;
} else {
result0 = null;
if (reportFailures === 0) {
matchFailed("[\\r\\n]");
}
}
return result0;
}
function parse_KW_MULTI_LINE_START() {
var result0;
if (input.substr(pos, 2) === "/*") {
result0 = "/*";
pos += 2;
} else {
result0 = null;
if (reportFailures === 0) {
matchFailed("\"/*\"");
}
}
return result0;
}
function parse_KW_MULTI_LINE_END() {
var result0;
if (input.substr(pos, 2) === "*/") {
result0 = "*/";
pos += 2;
} else {
result0 = null;
if (reportFailures === 0) {
matchFailed("\"*/\"");
}
}
return result0;
}
function parse___() {
var result0, result1;
result0 = [];
result1 = parse_whitespace();
while (result1 !== null) {
result0.push(result1);
result1 = parse_whitespace();
}
return result0;
}
function parse_whitespace() {
var result0;
if (/^[ \t\r\n]/.test(input.charAt(pos))) {
result0 = input.charAt(pos);
pos++;
} else {
result0 = null;
if (reportFailures === 0) {
matchFailed("[ \\t\\r\\n]");
}
}
return result0;
}
function cleanupExpected(expected) {
expected.sort();
var lastExpected = null;
var cleanExpected = [];
for (var i = 0; i < expected.length; i++) {
if (expected[i] !== lastExpected) {
cleanExpected.push(expected[i]);
lastExpected = expected[i];
}
}
return cleanExpected;
}
function computeErrorPosition() {
/*
* The first idea was to use |String.split| to break the input up to the
* error position along newlines and derive the line and column from
* there. However IE's |split| implementation is so broken that it was
* enough to prevent it.
*/
var line = 1;
var column = 1;
var seenCR = false;
for (var i = 0; i < Math.max(pos, rightmostFailuresPos); i++) {
var ch = input.charAt(i);
if (ch === "\n") {
if (!seenCR) { line++; }
column = 1;
seenCR = false;
} else if (ch === "\r" || ch === "\u2028" || ch === "\u2029") {
line++;
column = 1;
seenCR = true;
} else {
column++;
seenCR = false;
}
}
return { line: line, column: column };
}
var result = parseFunctions[startRule]();
/*
* The parser is now in one of the following three states:
*
* 1. The parser successfully parsed the whole input.
*
* - |result !== null|
* - |pos === input.length|
* - |rightmostFailuresExpected| may or may not contain something
*
* 2. The parser successfully parsed only a part of the input.
*
* - |result !== null|
* - |pos < input.length|
* - |rightmostFailuresExpected| may or may not contain something
*
* 3. The parser did not successfully parse any part of the input.
*
* - |result === null|
* - |pos === 0|
* - |rightmostFailuresExpected| contains at least one failure
*
* All code following this comment (including called functions) must
* handle these states.
*/
if (result === null || pos !== input.length) {
var offset = Math.max(pos, rightmostFailuresPos);
var found = offset < input.length ? input.charAt(offset) : null;
var errorPosition = computeErrorPosition();
throw new this.SyntaxError(
cleanupExpected(rightmostFailuresExpected),
found,
offset,
errorPosition.line,
errorPosition.column
);
}
return result;
},
/* Returns the parser source code. */
toSource: function() { return this._source; }
};
/* Thrown when a parser encounters a syntax error. */
result.SyntaxError = function(expected, found, offset, line, column) {
function buildMessage(expected, found) {
var expectedHumanized, foundHumanized;
switch (expected.length) {
case 0:
expectedHumanized = "end of input";
break;
case 1:
expectedHumanized = expected[0];
break;
default:
expectedHumanized = expected.slice(0, expected.length - 1).join(", ")
+ " or "
+ expected[expected.length - 1];
}
foundHumanized = found ? quote(found) : "end of input";
return "Expected " + expectedHumanized + " but " + foundHumanized + " found.";
}
this.name = "SyntaxError";
this.expected = expected;
this.found = found;
this.message = buildMessage(expected, found);
this.offset = offset;
this.line = line;
this.column = column;
};
result.SyntaxError.prototype = Error.prototype;
return result;
})();

File diff suppressed because it is too large Load Diff

View File

@ -1,87 +1,12 @@
const replaceStrFormIndexArr = require("../utils").replaceStrFormIndexArr; const replaceStrFormIndexArr = require("../utils").replaceStrFormIndexArr;
const commentFilter = require('../core/comment');
/** /**
* 过滤--注释 * 过滤--注释
* @param {String} sql * @param {String} sql
*/ */
function filterComments(sql) { function filterComments(sql) {
let tmpArr = []; return commentFilter.parse(sql)
const comments = [];
for (let i = 0; i < sql.length; i++) {
let char = sql[i];
//读取字符
if (char == "'" || char == "\"" || char == "-" || char == "\n" || char == "/" || char == "*") {
//推入数组
tmpArr.push({
index: i,
char: char
});
}
//校验数组是否有匹配语法
if (tmpArr.length < 2) {
if (tmpArr[0] && (tmpArr[0].char == "\n" || tmpArr[0].char == "*")) {
tmpArr = [];
}
continue;
}
let firstChar = tmpArr[0];
let lastChar = tmpArr[tmpArr.length - 1];
if (firstChar.char == "'" || firstChar.char == "\"") {
//引号匹配,则清空
if (lastChar.char == firstChar.char) {
tmpArr = [];
continue;
}
} else if (firstChar.char == "/") {
if (tmpArr[1].char != "*") {
tmpArr = [];
} else if (lastChar.char == "/") {
if (tmpArr.length > 3 && tmpArr[tmpArr.length - 2].char == "*") {
comments.push({
begin: firstChar.index,
end: lastChar.index
})
tmpArr = [];
}
}
continue;
} else if (firstChar.char == "-") {
//假如第一个是横线,则开始校验注释规则
//判断是否为两个注释符号,不是,则清空
if (tmpArr[1].char != "-") {
tmpArr = [];
continue;
}
//为注释作用域,遇到换行符,则结束注释
else if (lastChar.char == "\n") {
comments.push({
begin: firstChar.index,
end: lastChar.index
})
tmpArr = [];
continue;
}
//解析结束
else if (i == sql.length - 1) {
comments.push({
begin: firstChar.index,
end: i
})
continue;
}
} else {
tmpArr = [];
}
}
sql = replaceStrFormIndexArr(sql, '', comments)
return sql;
} }
/** /**
@ -89,7 +14,7 @@ function filterComments(sql) {
* @param {String} sql * @param {String} sql
*/ */
function cleanSql(sql) { function cleanSql(sql) {
return filterComments(sql).trim(); return filterComments(sql);
} }
/** /**

View File

@ -4,7 +4,8 @@
"description": "sql parser", "description": "sql parser",
"main": "index.js", "main": "index.js",
"scripts": { "scripts": {
"build": "pegjs peg/nquery.pegjs core/astParser.js" "build:parse": "pegjs peg/nquery.pegjs core/astParser.js",
"build:filter":"pegjs peg/comment.pegjs core/comment.js"
}, },
"author": "xiaokang", "author": "xiaokang",
"license": "ISC", "license": "ISC",

14
peg/build.js Normal file
View File

@ -0,0 +1,14 @@
const pegjs=require("pegjs");
const path=require("path");
const fs=require("fs");
const files=[{
source:path.resolve(process.cwd(),"./peg/comment.pegjs") ,
target:path.resolve(process.cwd(),"./core/comment.js") ,
},{
source:path.resolve(process.cwd(),"./peg/nquery.pegjs") ,
target:path.resolve(process.cwd(),"./core/astParser.js") ,
}];
const file=fs.readFileSync(files[0].source,{encoding:"utf8"})
pegjs.buildParser(file);

72
peg/comment.pegjs Normal file
View File

@ -0,0 +1,72 @@
start
= union_stmt:union_stmt
{
return union_stmt;
}
union_stmt
=stmt:
(
words:(!kw_start word:. {return word})*
stmt:(comment:comment {return ''}/quote:quote {return quote})
{return words.join("")+stmt}
)* other:.*
{return stmt.join("")+other.join("")}
comment
=comment:(multiLine/singleLine)
{
return comment;
}
singleLine
= start:KW_SINGLE_LINE_START
words:[^\r\n]*
{
return start+words.join("")
}
multiLine
=start:KW_MULTI_LINE_START
words:(!"*/" word:. {return word })*
end:KW_MULTI_LINE_END
{return start+words.join("")+end }
quote
=content:(
(
start:"\""
words:[^"]*
end:"\""
{return start+words.join("")+end;}
)
/
(
start:"'"
words:[^']*
end:"'"
{return start+words.join("")+end;}
)
)
kw_start=KW_SINGLE_LINE_START/KW_MULTI_LINE_START/"\""/"'"
KW_SINGLE_LINE_START = "--";
KW_SINGLE_LINE_END = [\r\n];
KW_MULTI_LINE_START = "/*";
KW_MULTI_LINE_END = "*/";
__ = whitespace*
whitespace
= [ \t\r\n];

View File

@ -160,7 +160,7 @@ start
} }
} }
init = { params = []; return true; } init = & { params = []; return true; }
union_stmt union_stmt
= head:select_stmt tail:(__ KW_UNION __ select_stmt)* { = head:select_stmt tail:(__ KW_UNION __ select_stmt)* {
@ -424,7 +424,7 @@ expr_list
expr_list_or_empty expr_list_or_empty
= l:expr_list = l:expr_list
/ { / & {
return { return {
type : 'expr_list', type : 'expr_list',
value : [] value : []
@ -931,7 +931,7 @@ proc_stmt
} }
} }
proc_init = { varList = []; return true; } proc_init = & { varList = []; return true; }
assign_stmt assign_stmt
= va:var_decl __ KW_ASSIGN __ e:proc_expr { = va:var_decl __ KW_ASSIGN __ e:proc_expr {

View File

@ -3,7 +3,7 @@ const example={
SELECT muyun_test_down1.id, muyun_test_down1.name, muyun_test_down2.age SELECT muyun_test_down1.id, muyun_test_down1.name, muyun_test_down2.age
FROM muyun_test_down1 FROM muyun_test_down1
JOIN muyun_test_down2 JOIN muyun_test_down2
ON muyun_test_down1.id = muyun_test_down2.id ON muyun_test_down1.id = muyun_test_down2.id
`, `,
test1:`/*asf*/create table sql_task_comment_test(id int comment 'id') comment 'sql test'; test1:`/*asf*/create table sql_task_comment_test(id int comment 'id') comment 'sql test';
--sdfsss`, --sdfsss`,

View File

@ -6,8 +6,8 @@ for(let [key,value] of testMap){
console.log(`******${key}********`) console.log(`******${key}********`)
console.log(value) console.log(value)
console.log(`******result********`) console.log(`******result********`)
console.log(dtSqlParser.parser.parse(value)); // console.log(dtSqlParser.parser.parse(value));
// console.log(dtSqlParser.filter.filterComments(value)) console.log(dtSqlParser.filter.filterComments(value))
console.log(`********************`) console.log(`********************`)
} }