abigwc/to_docx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

First commit.

Browse Source 
Signed-off-by: Chen Xiao <abigwc@gmail.com>
This commit is contained in:
Chen Xiao
2026-05-08 14:43:16 +08:00
commit 0b64e2de94
10989 changed files with 2253791 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
client/node_modules/@chevrotain/regexp-to-ast/LICENSE.txt
Generated Vendored
+202
View File
@@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
client/node_modules/@chevrotain/regexp-to-ast/lib/src/api.js
Generated Vendored
+3
View File
@@ -0,0 +1,3 @@
export { RegExpParser } from "./regexp-parser.js";
export { BaseRegExpVisitor } from "./base-regexp-visitor.js";
//# sourceMappingURL=api.js.map
client/node_modules/@chevrotain/regexp-to-ast/lib/src/api.js.map
Generated Vendored
+1
View File
@@ -0,0 +1 @@
{"version":3,"file":"api.js","sourceRoot":"","sources":["../../src/api.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAC;AAClD,OAAO,EAAE,iBAAiB,EAAE,MAAM,0BAA0B,CAAC"}
client/node_modules/@chevrotain/regexp-to-ast/lib/src/base-regexp-visitor.js
Generated Vendored
+94
View File
@@ -0,0 +1,94 @@
export class BaseRegExpVisitor {
visitChildren(node) {
for (const key in node) {
const child = node[key];
/* istanbul ignore else */
if (node.hasOwnProperty(key)) {
if (child.type !== undefined) {
this.visit(child);
}
else if (Array.isArray(child)) {
child.forEach((subChild) => {
this.visit(subChild);
}, this);
}
}
}
}
visit(node) {
switch (node.type) {
case "Pattern":
this.visitPattern(node);
break;
case "Flags":
this.visitFlags(node);
break;
case "Disjunction":
this.visitDisjunction(node);
break;
case "Alternative":
this.visitAlternative(node);
break;
case "StartAnchor":
this.visitStartAnchor(node);
break;
case "EndAnchor":
this.visitEndAnchor(node);
break;
case "WordBoundary":
this.visitWordBoundary(node);
break;
case "NonWordBoundary":
this.visitNonWordBoundary(node);
break;
case "Lookahead":
this.visitLookahead(node);
break;
case "NegativeLookahead":
this.visitNegativeLookahead(node);
break;
case "Lookbehind":
this.visitLookbehind(node);
break;
case "NegativeLookbehind":
this.visitNegativeLookbehind(node);
break;
case "Character":
this.visitCharacter(node);
break;
case "Set":
this.visitSet(node);
break;
case "Group":
this.visitGroup(node);
break;
case "GroupBackReference":
this.visitGroupBackReference(node);
break;
case "Quantifier":
this.visitQuantifier(node);
break;
}
this.visitChildren(node);
}
visitPattern(node) { }
visitFlags(node) { }
visitDisjunction(node) { }
visitAlternative(node) { }
// Assertion
visitStartAnchor(node) { }
visitEndAnchor(node) { }
visitWordBoundary(node) { }
visitNonWordBoundary(node) { }
visitLookahead(node) { }
visitNegativeLookahead(node) { }
visitLookbehind(node) { }
visitNegativeLookbehind(node) { }
// atoms
visitCharacter(node) { }
visitSet(node) { }
visitGroup(node) { }
visitGroupBackReference(node) { }
visitQuantifier(node) { }
}
//# sourceMappingURL=base-regexp-visitor.js.map
client/node_modules/@chevrotain/regexp-to-ast/lib/src/base-regexp-visitor.js.map
Generated Vendored
+1
View File
@@ -0,0 +1 @@
{"version":3,"file":"base-regexp-visitor.js","sourceRoot":"","sources":["../../src/base-regexp-visitor.ts"],"names":[],"mappings":"AAeA,MAAM,OAAO,iBAAiB;IACrB,aAAa,CAAC,IAAgB;QACnC,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YACvB,MAAM,KAAK,GAAI,IAAY,CAAC,GAAG,CAAC,CAAC;YACjC,0BAA0B;YAC1B,IAAI,IAAI,CAAC,cAAc,CAAC,GAAG,CAAC,EAAE,CAAC;gBAC7B,IAAI,KAAK,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;oBAC7B,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;gBACpB,CAAC;qBAAM,IAAI,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC;oBAChC,KAAK,CAAC,OAAO,CAAC,CAAC,QAAQ,EAAE,EAAE;wBACzB,IAAI,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC;oBACvB,CAAC,EAAE,IAAI,CAAC,CAAC;gBACX,CAAC;YACH,CAAC;QACH,CAAC;IACH,CAAC;IAEM,KAAK,CAAC,IAAmB;QAC9B,QAAQ,IAAI,CAAC,IAAI,EAAE,CAAC;YAClB,KAAK,SAAS;gBACZ,IAAI,CAAC,YAAY,CAAC,IAAI,CAAC,CAAC;gBACxB,MAAM;YACR,KAAK,OAAO;gBACV,IAAI,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC;gBACtB,MAAM;YACR,KAAK,aAAa;gBAChB,IAAI,CAAC,gBAAgB,CAAC,IAAI,CAAC,CAAC;gBAC5B,MAAM;YACR,KAAK,aAAa;gBAChB,IAAI,CAAC,gBAAgB,CAAC,IAAI,CAAC,CAAC;gBAC5B,MAAM;YACR,KAAK,aAAa;gBAChB,IAAI,CAAC,gBAAgB,CAAC,IAAI,CAAC,CAAC;gBAC5B,MAAM;YACR,KAAK,WAAW;gBACd,IAAI,CAAC,cAAc,CAAC,IAAI,CAAC,CAAC;gBAC1B,MAAM;YACR,KAAK,cAAc;gBACjB,IAAI,CAAC,iBAAiB,CAAC,IAAI,CAAC,CAAC;gBAC7B,MAAM;YACR,KAAK,iBAAiB;gBACpB,IAAI,CAAC,oBAAoB,CAAC,IAAI,CAAC,CAAC;gBAChC,MAAM;YACR,KAAK,WAAW;gBACd,IAAI,CAAC,cAAc,CAAC,IAAI,CAAC,CAAC;gBAC1B,MAAM;YACR,KAAK,mBAAmB;gBACtB,IAAI,CAAC,sBAAsB,CAAC,IAAI,CAAC,CAAC;gBAClC,MAAM;YACR,KAAK,YAAY;gBACf,IAAI,CAAC,eAAe,CAAC,IAAI,CAAC,CAAC;gBAC3B,MAAM;YACR,KAAK,oBAAoB;gBACvB,IAAI,CAAC,uBAAuB,CAAC,IAAI,CAAC,CAAC;gBACnC,MAAM;YACR,KAAK,WAAW;gBACd,IAAI,CAAC,cAAc,CAAC,IAAI,CAAC,CAAC;gBAC1B,MAAM;YACR,KAAK,KAAK;gBACR,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;gBACpB,MAAM;YACR,KAAK,OAAO;gBACV,IAAI,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC;gBACtB,MAAM;YACR,KAAK,oBAAoB;gBACvB,IAAI,CAAC,uBAAuB,CAAC,IAAI,CAAC,CAAC;gBACnC,MAAM;YACR,KAAK,YAAY;gBACf,IAAI,CAAC,eAAe,CAAC,IAAI,CAAC,CAAC;gBAC3B,MAAM;QACV,CAAC;QAED,IAAI,CAAC,aAAa,CAAC,IAAI,CAAC,CAAC;IAC3B,CAAC;IAEM,YAAY,CAAC,IAAmB,IAAS,CAAC;IAE1C,UAAU,CAAC,IAAiB,IAAS,CAAC;IAEtC,gBAAgB,CAAC,IAAiB,IAAS,CAAC;IAE5C,gBAAgB,CAAC,IAAiB,IAAS,CAAC;IAEnD,YAAY;IACL,gBAAgB,CAAC,IAAe,IAAS,CAAC;IAE1C,cAAc,CAAC,IAAe,IAAS,CAAC;IAExC,iBAAiB,CAAC,IAAe,IAAS,CAAC;IAE3C,oBAAoB,CAAC,IAAe,IAAS,CAAC;IAE9C,cAAc,CAAC,IAAe,IAAS,CAAC;IAExC,sBAAsB,CAAC,IAAe,IAAS,CAAC;IAEhD,eAAe,CAAC,IAAe,IAAS,CAAC;IAEzC,uBAAuB,CAAC,IAAe,IAAS,CAAC;IAExD,QAAQ;IACD,cAAc,CAAC,IAAe,IAAS,CAAC;IAExC,QAAQ,CAAC,IAAS,IAAS,CAAC;IAE5B,UAAU,CAAC,IAAW,IAAS,CAAC;IAEhC,uBAAuB,CAAC,IAAwB,IAAS,CAAC;IAE1D,eAAe,CAAC,IAAgB,IAAS,CAAC;CAClD"}
client/node_modules/@chevrotain/regexp-to-ast/lib/src/character-classes.js
Generated Vendored
+42
View File
@@ -0,0 +1,42 @@
import { cc } from "./utils.js";
export const digitsCharCodes = [];
for (let i = cc("0"); i <= cc("9"); i++) {
digitsCharCodes.push(i);
}
export const wordCharCodes = [cc("_")].concat(digitsCharCodes);
for (let i = cc("a"); i <= cc("z"); i++) {
wordCharCodes.push(i);
}
for (let i = cc("A"); i <= cc("Z"); i++) {
wordCharCodes.push(i);
}
// https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/RegExp#character-classes
export const whitespaceCodes = [
cc(" "),
cc("\f"),
cc("\n"),
cc("\r"),
cc("\t"),
cc("\v"),
cc("\t"),
cc("\u00a0"),
cc("\u1680"),
cc("\u2000"),
cc("\u2001"),
cc("\u2002"),
cc("\u2003"),
cc("\u2004"),
cc("\u2005"),
cc("\u2006"),
cc("\u2007"),
cc("\u2008"),
cc("\u2009"),
cc("\u200a"),
cc("\u2028"),
cc("\u2029"),
cc("\u202f"),
cc("\u205f"),
cc("\u3000"),
cc("\ufeff"),
];
//# sourceMappingURL=character-classes.js.map
client/node_modules/@chevrotain/regexp-to-ast/lib/src/character-classes.js.map
Generated Vendored
+1
View File
@@ -0,0 +1 @@
{"version":3,"file":"character-classes.js","sourceRoot":"","sources":["../../src/character-classes.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,EAAE,EAAE,MAAM,YAAY,CAAC;AAEhC,MAAM,CAAC,MAAM,eAAe,GAAa,EAAE,CAAC;AAC5C,KAAK,IAAI,CAAC,GAAG,EAAE,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,EAAE,CAAC,GAAG,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC;IACxC,eAAe,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAC1B,CAAC;AAED,MAAM,CAAC,MAAM,aAAa,GAAa,CAAC,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC,MAAM,CAAC,eAAe,CAAC,CAAC;AACzE,KAAK,IAAI,CAAC,GAAG,EAAE,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,EAAE,CAAC,GAAG,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC;IACxC,aAAa,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AACxB,CAAC;AAED,KAAK,IAAI,CAAC,GAAG,EAAE,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,EAAE,CAAC,GAAG,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC;IACxC,aAAa,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AACxB,CAAC;AAED,4GAA4G;AAC5G,MAAM,CAAC,MAAM,eAAe,GAAa;IACv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b,CAAC"}
client/node_modules/@chevrotain/regexp-to-ast/lib/src/regexp-parser.js
Generated Vendored
+744
View File
@@ -0,0 +1,744 @@
import { addFlag, ASSERT_EXISTS, ASSERT_NEVER_REACH_HERE, cc, insertToSet, isCharacter, } from "./utils.js";
import { digitsCharCodes, whitespaceCodes, wordCharCodes, } from "./character-classes.js";
// consts and utilities
const hexDigitPattern = /[0-9a-fA-F]/;
const decimalPattern = /[0-9]/;
const decimalPatternNoZero = /[1-9]/;
// https://hackernoon.com/the-madness-of-parsing-real-world-javascript-regexps-d9ee336df983
// https://www.ecma-international.org/ecma-262/8.0/index.html#prod-Pattern
export class RegExpParser {
constructor() {
this.idx = 0;
this.input = "";
this.groupIdx = 0;
}
saveState() {
return {
idx: this.idx,
input: this.input,
groupIdx: this.groupIdx,
};
}
restoreState(newState) {
this.idx = newState.idx;
this.input = newState.input;
this.groupIdx = newState.groupIdx;
}
pattern(input) {
// parser state
this.idx = 0;
this.input = input;
this.groupIdx = 0;
this.consumeChar("/");
const value = this.disjunction();
this.consumeChar("/");
const flags = {
type: "Flags",
loc: { begin: this.idx, end: input.length },
global: false,
ignoreCase: false,
multiLine: false,
unicode: false,
sticky: false,
};
while (this.isRegExpFlag()) {
switch (this.popChar()) {
case "g":
addFlag(flags, "global");
break;
case "i":
addFlag(flags, "ignoreCase");
break;
case "m":
addFlag(flags, "multiLine");
break;
case "u":
addFlag(flags, "unicode");
break;
case "y":
addFlag(flags, "sticky");
break;
}
}
if (this.idx !== this.input.length) {
throw Error("Redundant input: " + this.input.substring(this.idx));
}
return {
type: "Pattern",
flags: flags,
value: value,
loc: this.loc(0),
};
}
disjunction() {
const alts = [];
const begin = this.idx;
alts.push(this.alternative());
while (this.peekChar() === "|") {
this.consumeChar("|");
alts.push(this.alternative());
}
return { type: "Disjunction", value: alts, loc: this.loc(begin) };
}
alternative() {
const terms = [];
const begin = this.idx;
while (this.isTerm()) {
terms.push(this.term());
}
return { type: "Alternative", value: terms, loc: this.loc(begin) };
}
term() {
if (this.isAssertion()) {
return this.assertion();
}
else {
return this.atom();
}
}
assertion() {
const begin = this.idx;
switch (this.popChar()) {
case "^":
return {
type: "StartAnchor",
loc: this.loc(begin),
};
case "$":
return { type: "EndAnchor", loc: this.loc(begin) };
// '\b' or '\B'
case "\\":
switch (this.popChar()) {
case "b":
return {
type: "WordBoundary",
loc: this.loc(begin),
};
case "B":
return {
type: "NonWordBoundary",
loc: this.loc(begin),
};
}
/* c8 ignore next */
throw Error("Invalid Assertion Escape");
// '(?=' or '(?!'
case "(":
this.consumeChar("?");
let type;
switch (this.popChar()) {
case "=":
type = "Lookahead";
break;
case "!":
type = "NegativeLookahead";
break;
case "<": {
switch (this.popChar()) {
case "=":
type = "Lookbehind";
break;
case "!":
type = "NegativeLookbehind";
}
break;
}
}
ASSERT_EXISTS(type);
const disjunction = this.disjunction();
this.consumeChar(")");
return {
type: type,
value: disjunction,
loc: this.loc(begin),
};
}
// istanbul ignore next
return ASSERT_NEVER_REACH_HERE();
}
quantifier(isBacktracking = false) {
let range = undefined;
const begin = this.idx;
switch (this.popChar()) {
case "*":
range = {
atLeast: 0,
atMost: Infinity,
};
break;
case "+":
range = {
atLeast: 1,
atMost: Infinity,
};
break;
case "?":
range = {
atLeast: 0,
atMost: 1,
};
break;
case "{":
const atLeast = this.integerIncludingZero();
switch (this.popChar()) {
case "}":
range = {
atLeast: atLeast,
atMost: atLeast,
};
break;
case ",":
let atMost;
if (this.isDigit()) {
atMost = this.integerIncludingZero();
range = {
atLeast: atLeast,
atMost: atMost,
};
}
else {
range = {
atLeast: atLeast,
atMost: Infinity,
};
}
this.consumeChar("}");
break;
}
// throwing exceptions from "ASSERT_EXISTS" during backtracking
// causes severe performance degradations
if (isBacktracking === true && range === undefined) {
return undefined;
}
ASSERT_EXISTS(range);
break;
}
// throwing exceptions from "ASSERT_EXISTS" during backtracking
// causes severe performance degradations
if (isBacktracking === true && range === undefined) {
return undefined;
}
// istanbul ignore else
if (ASSERT_EXISTS(range)) {
if (this.peekChar(0) === "?") {
this.consumeChar("?");
range.greedy = false;
}
else {
range.greedy = true;
}
range.type = "Quantifier";
range.loc = this.loc(begin);
return range;
}
}
atom() {
let atom;
const begin = this.idx;
switch (this.peekChar()) {
case ".":
atom = this.dotAll();
break;
case "\\":
atom = this.atomEscape();
break;
case "[":
atom = this.characterClass();
break;
case "(":
atom = this.group();
break;
}
if (atom === undefined && this.isPatternCharacter()) {
atom = this.patternCharacter();
}
// istanbul ignore else
if (ASSERT_EXISTS(atom)) {
atom.loc = this.loc(begin);
if (this.isQuantifier()) {
atom.quantifier = this.quantifier();
}
return atom;
}
// istanbul ignore next
return ASSERT_NEVER_REACH_HERE();
}
dotAll() {
this.consumeChar(".");
return {
type: "Set",
complement: true,
value: [cc("\n"), cc("\r"), cc("\u2028"), cc("\u2029")],
};
}
atomEscape() {
this.consumeChar("\\");
switch (this.peekChar()) {
case "1":
case "2":
case "3":
case "4":
case "5":
case "6":
case "7":
case "8":
case "9":
return this.decimalEscapeAtom();
case "d":
case "D":
case "s":
case "S":
case "w":
case "W":
return this.characterClassEscape();
case "f":
case "n":
case "r":
case "t":
case "v":
return this.controlEscapeAtom();
case "c":
return this.controlLetterEscapeAtom();
case "0":
return this.nulCharacterAtom();
case "x":
return this.hexEscapeSequenceAtom();
case "u":
return this.regExpUnicodeEscapeSequenceAtom();
default:
return this.identityEscapeAtom();
}
}
decimalEscapeAtom() {
const value = this.positiveInteger();
return { type: "GroupBackReference", value: value };
}
characterClassEscape() {
let set;
let complement = false;
switch (this.popChar()) {
case "d":
set = digitsCharCodes;
break;
case "D":
set = digitsCharCodes;
complement = true;
break;
case "s":
set = whitespaceCodes;
break;
case "S":
set = whitespaceCodes;
complement = true;
break;
case "w":
set = wordCharCodes;
break;
case "W":
set = wordCharCodes;
complement = true;
break;
}
// istanbul ignore else
if (ASSERT_EXISTS(set)) {
return { type: "Set", value: set, complement: complement };
}
// istanbul ignore next
return ASSERT_NEVER_REACH_HERE();
}
controlEscapeAtom() {
let escapeCode;
switch (this.popChar()) {
case "f":
escapeCode = cc("\f");
break;
case "n":
escapeCode = cc("\n");
break;
case "r":
escapeCode = cc("\r");
break;
case "t":
escapeCode = cc("\t");
break;
case "v":
escapeCode = cc("\v");
break;
}
// istanbul ignore else
if (ASSERT_EXISTS(escapeCode)) {
return { type: "Character", value: escapeCode };
}
// istanbul ignore next
return ASSERT_NEVER_REACH_HERE();
}
controlLetterEscapeAtom() {
this.consumeChar("c");
const letter = this.popChar();
if (/[a-zA-Z]/.test(letter) === false) {
throw Error("Invalid ");
}
const letterCode = letter.toUpperCase().charCodeAt(0) - 64;
return { type: "Character", value: letterCode };
}
nulCharacterAtom() {
// TODO implement '[lookahead ∉ DecimalDigit]'
// TODO: for the deprecated octal escape sequence
this.consumeChar("0");
return { type: "Character", value: cc("\0") };
}
hexEscapeSequenceAtom() {
this.consumeChar("x");
return this.parseHexDigits(2);
}
regExpUnicodeEscapeSequenceAtom() {
this.consumeChar("u");
return this.parseHexDigits(4);
}
identityEscapeAtom() {
// TODO: implement "SourceCharacter but not UnicodeIDContinue"
// // http://unicode.org/reports/tr31/#Specific_Character_Adjustments
const escapedChar = this.popChar();
return { type: "Character", value: cc(escapedChar) };
}
classPatternCharacterAtom() {
switch (this.peekChar()) {
// istanbul ignore next
case "\n":
// istanbul ignore next
case "\r":
// istanbul ignore next
case "\u2028":
// istanbul ignore next
case "\u2029":
// istanbul ignore next
case "\\":
// istanbul ignore next
case "]":
throw Error("TBD");
default:
const nextChar = this.popChar();
return { type: "Character", value: cc(nextChar) };
}
}
characterClass() {
const set = [];
let complement = false;
this.consumeChar("[");
if (this.peekChar(0) === "^") {
this.consumeChar("^");
complement = true;
}
while (this.isClassAtom()) {
const from = this.classAtom();
const isFromSingleChar = from.type === "Character";
if (isCharacter(from) && this.isRangeDash()) {
this.consumeChar("-");
const to = this.classAtom();
const isToSingleChar = to.type === "Character";
// a range can only be used when both sides are single characters
if (isCharacter(to)) {
if (to.value < from.value) {
throw Error("Range out of order in character class");
}
set.push({ from: from.value, to: to.value });
}
else {
// literal dash
insertToSet(from.value, set);
set.push(cc("-"));
insertToSet(to.value, set);
}
}
else {
insertToSet(from.value, set);
}
}
this.consumeChar("]");
return { type: "Set", complement: complement, value: set };
}
classAtom() {
switch (this.peekChar()) {
// istanbul ignore next
case "]":
// istanbul ignore next
case "\n":
// istanbul ignore next
case "\r":
// istanbul ignore next
case "\u2028":
// istanbul ignore next
case "\u2029":
throw Error("TBD");
case "\\":
return this.classEscape();
default:
return this.classPatternCharacterAtom();
}
}
classEscape() {
this.consumeChar("\\");
switch (this.peekChar()) {
// Matches a backspace.
// (Not to be confused with \b word boundary outside characterClass)
case "b":
this.consumeChar("b");
return { type: "Character", value: cc("\u0008") };
case "d":
case "D":
case "s":
case "S":
case "w":
case "W":
return this.characterClassEscape();
case "f":
case "n":
case "r":
case "t":
case "v":
return this.controlEscapeAtom();
case "c":
return this.controlLetterEscapeAtom();
case "0":
return this.nulCharacterAtom();
case "x":
return this.hexEscapeSequenceAtom();
case "u":
return this.regExpUnicodeEscapeSequenceAtom();
default:
return this.identityEscapeAtom();
}
}
group() {
let capturing = true;
this.consumeChar("(");
switch (this.peekChar(0)) {
case "?":
this.consumeChar("?");
this.consumeChar(":");
capturing = false;
break;
default:
this.groupIdx++;
break;
}
const value = this.disjunction();
this.consumeChar(")");
const groupAst = {
type: "Group",
capturing: capturing,
value: value,
};
if (capturing) {
groupAst["idx"] = this.groupIdx;
}
return groupAst;
}
positiveInteger() {
let number = this.popChar();
// istanbul ignore next - can't ever get here due to previous lookahead checks
// still implementing this error checking in case this ever changes.
if (decimalPatternNoZero.test(number) === false) {
throw Error("Expecting a positive integer");
}
while (decimalPattern.test(this.peekChar(0))) {
number += this.popChar();
}
return parseInt(number, 10);
}
integerIncludingZero() {
let number = this.popChar();
if (decimalPattern.test(number) === false) {
throw Error("Expecting an integer");
}
while (decimalPattern.test(this.peekChar(0))) {
number += this.popChar();
}
return parseInt(number, 10);
}
patternCharacter() {
const nextChar = this.popChar();
switch (nextChar) {
// istanbul ignore next
case "\n":
// istanbul ignore next
case "\r":
// istanbul ignore next
case "\u2028":
// istanbul ignore next
case "\u2029":
// istanbul ignore next
case "^":
// istanbul ignore next
case "$":
// istanbul ignore next
case "\\":
// istanbul ignore next
case ".":
// istanbul ignore next
case "*":
// istanbul ignore next
case "+":
// istanbul ignore next
case "?":
// istanbul ignore next
case "(":
// istanbul ignore next
case ")":
// istanbul ignore next
case "[":
// istanbul ignore next
case "|":
// istanbul ignore next
throw Error("TBD");
default:
return { type: "Character", value: cc(nextChar) };
}
}
isRegExpFlag() {
switch (this.peekChar(0)) {
case "g":
case "i":
case "m":
case "u":
case "y":
return true;
default:
return false;
}
}
isRangeDash() {
return this.peekChar() === "-" && this.isClassAtom(1);
}
isDigit() {
return decimalPattern.test(this.peekChar(0));
}
isClassAtom(howMuch = 0) {
switch (this.peekChar(howMuch)) {
case "]":
case "\n":
case "\r":
case "\u2028":
case "\u2029":
return false;
default:
return true;
}
}
isTerm() {
return this.isAtom() || this.isAssertion();
}
isAtom() {
if (this.isPatternCharacter()) {
return true;
}
switch (this.peekChar(0)) {
case ".":
case "\\": // atomEscape
case "[": // characterClass
// TODO: isAtom must be called before isAssertion - disambiguate
case "(": // group
return true;
default:
return false;
}
}
isAssertion() {
switch (this.peekChar(0)) {
case "^":
case "$":
return true;
// '\b' or '\B'
case "\\":
switch (this.peekChar(1)) {
case "b":
case "B":
return true;
default:
return false;
}
// '(?=' or '(?!' or `(?<=` or `(?<!`
case "(":
return (this.peekChar(1) === "?" &&
(this.peekChar(2) === "=" ||
this.peekChar(2) === "!" ||
(this.peekChar(2) === "<" &&
(this.peekChar(3) === "=" || this.peekChar(3) === "!"))));
default:
return false;
}
}
isQuantifier() {
const prevState = this.saveState();
try {
return this.quantifier(true) !== undefined;
}
catch (e) {
return false;
}
finally {
this.restoreState(prevState);
}
}
isPatternCharacter() {
switch (this.peekChar()) {
case "^":
case "$":
case "\\":
case ".":
case "*":
case "+":
case "?":
case "(":
case ")":
case "[":
case "|":
case "/":
case "\n":
case "\r":
case "\u2028":
case "\u2029":
return false;
default:
return true;
}
}
parseHexDigits(howMany) {
let hexString = "";
for (let i = 0; i < howMany; i++) {
const hexChar = this.popChar();
if (hexDigitPattern.test(hexChar) === false) {
throw Error("Expecting a HexDecimal digits");
}
hexString += hexChar;
}
const charCode = parseInt(hexString, 16);
return { type: "Character", value: charCode };
}
peekChar(howMuch = 0) {
return this.input[this.idx + howMuch];
}
popChar() {
const nextChar = this.peekChar(0);
this.consumeChar(undefined);
return nextChar;
}
consumeChar(char) {
if (char !== undefined && this.input[this.idx] !== char) {
throw Error("Expected: '" +
char +
"' but found: '" +
this.input[this.idx] +
"' at offset: " +
this.idx);
}
if (this.idx >= this.input.length) {
throw Error("Unexpected end of input");
}
this.idx++;
}
loc(begin) {
return { begin: begin, end: this.idx };
}
}
//# sourceMappingURL=regexp-parser.js.map
client/node_modules/@chevrotain/regexp-to-ast/lib/src/regexp-parser.js.map
Generated Vendored
+1
View File
File diff suppressed because one or more lines are too long
client/node_modules/@chevrotain/regexp-to-ast/lib/src/utils.js
Generated Vendored
+35
View File
@@ -0,0 +1,35 @@
export function cc(char) {
return char.charCodeAt(0);
}
export function insertToSet(item, set) {
if (Array.isArray(item)) {
item.forEach(function (subItem) {
set.push(subItem);
});
}
else {
set.push(item);
}
}
export function addFlag(flagObj, flagKey) {
if (flagObj[flagKey] === true) {
throw "duplicate flag " + flagKey;
}
const x = flagObj[flagKey];
flagObj[flagKey] = true;
}
export function ASSERT_EXISTS(obj) {
// istanbul ignore next
if (obj === undefined) {
throw Error("Internal Error - Should never get here!");
}
return true;
}
// istanbul ignore next
export function ASSERT_NEVER_REACH_HERE() {
throw Error("Internal Error - Should never get here!");
}
export function isCharacter(obj) {
return obj["type"] === "Character";
}
//# sourceMappingURL=utils.js.map
client/node_modules/@chevrotain/regexp-to-ast/lib/src/utils.js.map
Generated Vendored
+1
View File
@@ -0,0 +1 @@
{"version":3,"file":"utils.js","sourceRoot":"","sources":["../../src/utils.ts"],"names":[],"mappings":"AAEA,MAAM,UAAU,EAAE,CAAC,IAAY;IAC7B,OAAO,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC;AAC5B,CAAC;AAED,MAAM,UAAU,WAAW,CAAI,IAAa,EAAE,GAAQ;IACpD,IAAI,KAAK,CAAC,OAAO,CAAC,IAAI,CAAC,EAAE,CAAC;QACxB,IAAI,CAAC,OAAO,CAAC,UAAU,OAAO;YAC5B,GAAG,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;QACpB,CAAC,CAAC,CAAC;IACL,CAAC;SAAM,CAAC;QACN,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IACjB,CAAC;AACH,CAAC;AAED,MAAM,UAAU,OAAO,CACrB,OAAoB,EACpB,OAAkD;IAElD,IAAI,OAAO,CAAC,OAAO,CAAC,KAAK,IAAI,EAAE,CAAC;QAC9B,MAAM,iBAAiB,GAAG,OAAO,CAAC;IACpC,CAAC;IAED,MAAM,CAAC,GAAY,OAAO,CAAC,OAAO,CAAC,CAAC;IACpC,OAAO,CAAC,OAAO,CAAC,GAAG,IAAI,CAAC;AAC1B,CAAC;AAED,MAAM,UAAU,aAAa,CAAa,GAAQ;IAChD,uBAAuB;IACvB,IAAI,GAAG,KAAK,SAAS,EAAE,CAAC;QACtB,MAAM,KAAK,CAAC,yCAAyC,CAAC,CAAC;IACzD,CAAC;IACD,OAAO,IAAI,CAAC;AACd,CAAC;AAED,uBAAuB;AACvB,MAAM,UAAU,uBAAuB;IACrC,MAAM,KAAK,CAAC,yCAAyC,CAAC,CAAC;AACzD,CAAC;AAED,MAAM,UAAU,WAAW,CAAC,GAAqB;IAC/C,OAAO,GAAG,CAAC,MAAM,CAAC,KAAK,WAAW,CAAC;AACrC,CAAC"}
client/node_modules/@chevrotain/regexp-to-ast/package.json
Generated Vendored
+47
View File
@@ -0,0 +1,47 @@
{
"name": "@chevrotain/regexp-to-ast",
"version": "12.0.0",
"description": "Parses a Regular Expression and outputs an AST",
"keywords": [
"regExp",
"parser",
"regular expression"
],
"bugs": {
"url": "https://github.com/Chevrotain/chevrotain/issues"
},
"license": "Apache-2.0",
"type": "module",
"types": "./types.d.ts",
"exports": {
".": {
"import": "./lib/src/api.js",
"types": "./types.d.ts"
}
},
"files": [
"lib/src/**/*.js",
"lib/src/**/*.map",
"src/**/*.ts",
"types.d.ts"
],
"repository": {
"type": "git",
"url": "git://github.com/Chevrotain/chevrotain.git"
},
"scripts": {
"---------- CI FLOWS --------": "",
"ci": "pnpm run build test",
"build": "npm-run-all clean compile",
"test": "npm-run-all coverage",
"---------- BUILD STEPS --------": "",
"clean": "shx rm -rf lib coverage",
"compile:watch": "tsc -w",
"compile": "tsc",
"coverage": "c8 mocha"
},
"publishConfig": {
"access": "public"
},
"gitHead": "d3b4d05d5dd53d53d27175119bc7c9ed8056e3d5"
}
client/node_modules/@chevrotain/regexp-to-ast/src/api.ts
Generated Vendored
+2
View File
@@ -0,0 +1,2 @@
export { RegExpParser } from "./regexp-parser.js";
export { BaseRegExpVisitor } from "./base-regexp-visitor.js";
client/node_modules/@chevrotain/regexp-to-ast/src/base-regexp-visitor.ts
Generated Vendored
+126
View File
@@ -0,0 +1,126 @@
import type {
Alternative,
Assertion,
Character,
Disjunction,
Group,
GroupBackReference,
IRegExpAST,
Quantifier,
RegExpAstPart,
RegExpFlags,
RegExpPattern,
Set,
} from "../types";
export class BaseRegExpVisitor {
public visitChildren(node: IRegExpAST) {
for (const key in node) {
const child = (node as any)[key];
/* istanbul ignore else */
if (node.hasOwnProperty(key)) {
if (child.type !== undefined) {
this.visit(child);
} else if (Array.isArray(child)) {
child.forEach((subChild) => {
this.visit(subChild);
}, this);
}
}
}
}
public visit(node: RegExpAstPart): void {
switch (node.type) {
case "Pattern":
this.visitPattern(node);
break;
case "Flags":
this.visitFlags(node);
break;
case "Disjunction":
this.visitDisjunction(node);
break;
case "Alternative":
this.visitAlternative(node);
break;
case "StartAnchor":
this.visitStartAnchor(node);
break;
case "EndAnchor":
this.visitEndAnchor(node);
break;
case "WordBoundary":
this.visitWordBoundary(node);
break;
case "NonWordBoundary":
this.visitNonWordBoundary(node);
break;
case "Lookahead":
this.visitLookahead(node);
break;
case "NegativeLookahead":
this.visitNegativeLookahead(node);
break;
case "Lookbehind":
this.visitLookbehind(node);
break;
case "NegativeLookbehind":
this.visitNegativeLookbehind(node);
break;
case "Character":
this.visitCharacter(node);
break;
case "Set":
this.visitSet(node);
break;
case "Group":
this.visitGroup(node);
break;
case "GroupBackReference":
this.visitGroupBackReference(node);
break;
case "Quantifier":
this.visitQuantifier(node);
break;
}
this.visitChildren(node);
}
public visitPattern(node: RegExpPattern): void {}
public visitFlags(node: RegExpFlags): void {}
public visitDisjunction(node: Disjunction): void {}
public visitAlternative(node: Alternative): void {}
// Assertion
public visitStartAnchor(node: Assertion): void {}
public visitEndAnchor(node: Assertion): void {}
public visitWordBoundary(node: Assertion): void {}
public visitNonWordBoundary(node: Assertion): void {}
public visitLookahead(node: Assertion): void {}
public visitNegativeLookahead(node: Assertion): void {}
public visitLookbehind(node: Assertion): void {}
public visitNegativeLookbehind(node: Assertion): void {}
// atoms
public visitCharacter(node: Character): void {}
public visitSet(node: Set): void {}
public visitGroup(node: Group): void {}
public visitGroupBackReference(node: GroupBackReference): void {}
public visitQuantifier(node: Quantifier): void {}
}
client/node_modules/@chevrotain/regexp-to-ast/src/character-classes.ts
Generated Vendored
+45
View File
@@ -0,0 +1,45 @@
import { cc } from "./utils.js";
export const digitsCharCodes: number[] = [];
for (let i = cc("0"); i <= cc("9"); i++) {
digitsCharCodes.push(i);
}
export const wordCharCodes: number[] = [cc("_")].concat(digitsCharCodes);
for (let i = cc("a"); i <= cc("z"); i++) {
wordCharCodes.push(i);
}
for (let i = cc("A"); i <= cc("Z"); i++) {
wordCharCodes.push(i);
}
// https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/RegExp#character-classes
export const whitespaceCodes: number[] = [
cc(" "),
cc("\f"),
cc("\n"),
cc("\r"),
cc("\t"),
cc("\v"),
cc("\t"),
cc("\u00a0"),
cc("\u1680"),
cc("\u2000"),
cc("\u2001"),
cc("\u2002"),
cc("\u2003"),
cc("\u2004"),
cc("\u2005"),
cc("\u2006"),
cc("\u2007"),
cc("\u2008"),
cc("\u2009"),
cc("\u200a"),
cc("\u2028"),
cc("\u2029"),
cc("\u202f"),
cc("\u205f"),
cc("\u3000"),
cc("\ufeff"),
];
client/node_modules/@chevrotain/regexp-to-ast/src/regexp-parser.ts
Generated Vendored
+858
View File
@@ -0,0 +1,858 @@
import type {
Alternative,
Assertion,
Atom,
Character,
Disjunction,
Group,
GroupBackReference,
Location,
Quantifier,
Range,
RegExpFlags,
RegExpPattern,
Set,
Term,
} from "../types";
import {
addFlag,
ASSERT_EXISTS,
ASSERT_NEVER_REACH_HERE,
cc,
insertToSet,
isCharacter,
} from "./utils.js";
import {
digitsCharCodes,
whitespaceCodes,
wordCharCodes,
} from "./character-classes.js";
// consts and utilities
const hexDigitPattern = /[0-9a-fA-F]/;
const decimalPattern = /[0-9]/;
const decimalPatternNoZero = /[1-9]/;
// https://hackernoon.com/the-madness-of-parsing-real-world-javascript-regexps-d9ee336df983
// https://www.ecma-international.org/ecma-262/8.0/index.html#prod-Pattern
export class RegExpParser {
protected idx: number = 0;
protected input: string = "";
protected groupIdx: number = 0;
protected saveState() {
return {
idx: this.idx,
input: this.input,
groupIdx: this.groupIdx,
};
}
protected restoreState(newState: {
idx: number;
input: string;
groupIdx: number;
}) {
this.idx = newState.idx;
this.input = newState.input;
this.groupIdx = newState.groupIdx;
}
public pattern(input: string): RegExpPattern {
// parser state
this.idx = 0;
this.input = input;
this.groupIdx = 0;
this.consumeChar("/");
const value = this.disjunction();
this.consumeChar("/");
const flags: RegExpFlags = {
type: "Flags",
loc: { begin: this.idx, end: input.length },
global: false,
ignoreCase: false,
multiLine: false,
unicode: false,
sticky: false,
};
while (this.isRegExpFlag()) {
switch (this.popChar()) {
case "g":
addFlag(flags, "global");
break;
case "i":
addFlag(flags, "ignoreCase");
break;
case "m":
addFlag(flags, "multiLine");
break;
case "u":
addFlag(flags, "unicode");
break;
case "y":
addFlag(flags, "sticky");
break;
}
}
if (this.idx !== this.input.length) {
throw Error("Redundant input: " + this.input.substring(this.idx));
}
return {
type: "Pattern",
flags: flags,
value: value,
loc: this.loc(0),
};
}
protected disjunction(): Disjunction {
const alts = [];
const begin = this.idx;
alts.push(this.alternative());
while (this.peekChar() === "|") {
this.consumeChar("|");
alts.push(this.alternative());
}
return { type: "Disjunction", value: alts, loc: this.loc(begin) };
}
protected alternative(): Alternative {
const terms = [];
const begin = this.idx;
while (this.isTerm()) {
terms.push(this.term());
}
return { type: "Alternative", value: terms, loc: this.loc(begin) };
}
protected term(): Term {
if (this.isAssertion()) {
return this.assertion();
} else {
return this.atom();
}
}
protected assertion(): Assertion {
const begin = this.idx;
switch (this.popChar()) {
case "^":
return {
type: "StartAnchor",
loc: this.loc(begin),
};
case "$":
return { type: "EndAnchor", loc: this.loc(begin) };
// '\b' or '\B'
case "\\":
switch (this.popChar()) {
case "b":
return {
type: "WordBoundary",
loc: this.loc(begin),
};
case "B":
return {
type: "NonWordBoundary",
loc: this.loc(begin),
};
}
/* c8 ignore next */
throw Error("Invalid Assertion Escape");
// '(?=' or '(?!'
case "(":
this.consumeChar("?");
let type:
| "Lookahead"
| "NegativeLookahead"
| "Lookbehind"
| "NegativeLookbehind"
| undefined;
switch (this.popChar()) {
case "=":
type = "Lookahead";
break;
case "!":
type = "NegativeLookahead";
break;
case "<": {
switch (this.popChar()) {
case "=":
type = "Lookbehind";
break;
case "!":
type = "NegativeLookbehind";
}
break;
}
}
ASSERT_EXISTS(type);
const disjunction = this.disjunction();
this.consumeChar(")");
return {
type: type!,
value: disjunction,
loc: this.loc(begin),
};
}
// istanbul ignore next
return ASSERT_NEVER_REACH_HERE();
}
protected quantifier(
isBacktracking: boolean = false,
): Quantifier | undefined {
let range: Partial<Quantifier> | undefined = undefined;
const begin = this.idx;
switch (this.popChar()) {
case "*":
range = {
atLeast: 0,
atMost: Infinity,
};
break;
case "+":
range = {
atLeast: 1,
atMost: Infinity,
};
break;
case "?":
range = {
atLeast: 0,
atMost: 1,
};
break;
case "{":
const atLeast = this.integerIncludingZero();
switch (this.popChar()) {
case "}":
range = {
atLeast: atLeast,
atMost: atLeast,
};
break;
case ",":
let atMost;
if (this.isDigit()) {
atMost = this.integerIncludingZero();
range = {
atLeast: atLeast,
atMost: atMost,
};
} else {
range = {
atLeast: atLeast,
atMost: Infinity,
};
}
this.consumeChar("}");
break;
}
// throwing exceptions from "ASSERT_EXISTS" during backtracking
// causes severe performance degradations
if (isBacktracking === true && range === undefined) {
return undefined;
}
ASSERT_EXISTS(range);
break;
}
// throwing exceptions from "ASSERT_EXISTS" during backtracking
// causes severe performance degradations
if (isBacktracking === true && range === undefined) {
return undefined;
}
// istanbul ignore else
if (ASSERT_EXISTS(range)) {
if (this.peekChar(0) === "?") {
this.consumeChar("?");
range.greedy = false;
} else {
range.greedy = true;
}
range.type = "Quantifier";
range.loc = this.loc(begin);
return range as Quantifier;
}
}
protected atom(): Atom {
let atom: Omit<Atom, "loc" | "type"> | undefined;
const begin = this.idx;
switch (this.peekChar()) {
case ".":
atom = this.dotAll();
break;
case "\\":
atom = this.atomEscape();
break;
case "[":
atom = this.characterClass();
break;
case "(":
atom = this.group();
break;
}
if (atom === undefined && this.isPatternCharacter()) {
atom = this.patternCharacter();
}
// istanbul ignore else
if (ASSERT_EXISTS<Atom>(atom)) {
atom.loc = this.loc(begin);
if (this.isQuantifier()) {
atom.quantifier = this.quantifier();
}
return atom;
}
// istanbul ignore next
return ASSERT_NEVER_REACH_HERE();
}
protected dotAll(): Omit<Set, "loc"> {
this.consumeChar(".");
return {
type: "Set",
complement: true,
value: [cc("\n"), cc("\r"), cc("\u2028"), cc("\u2029")],
};
}
protected atomEscape(): Omit<GroupBackReference | Set | Character, "loc"> {
this.consumeChar("\\");
switch (this.peekChar()) {
case "1":
case "2":
case "3":
case "4":
case "5":
case "6":
case "7":
case "8":
case "9":
return this.decimalEscapeAtom();
case "d":
case "D":
case "s":
case "S":
case "w":
case "W":
return this.characterClassEscape();
case "f":
case "n":
case "r":
case "t":
case "v":
return this.controlEscapeAtom();
case "c":
return this.controlLetterEscapeAtom();
case "0":
return this.nulCharacterAtom();
case "x":
return this.hexEscapeSequenceAtom();
case "u":
return this.regExpUnicodeEscapeSequenceAtom();
default:
return this.identityEscapeAtom();
}
}
protected decimalEscapeAtom(): Omit<GroupBackReference, "loc"> {
const value = this.positiveInteger();
return { type: "GroupBackReference", value: value };
}
protected characterClassEscape(): Omit<Set, "loc"> {
let set: (number | Range)[] | undefined;
let complement = false;
switch (this.popChar()) {
case "d":
set = digitsCharCodes;
break;
case "D":
set = digitsCharCodes;
complement = true;
break;
case "s":
set = whitespaceCodes;
break;
case "S":
set = whitespaceCodes;
complement = true;
break;
case "w":
set = wordCharCodes;
break;
case "W":
set = wordCharCodes;
complement = true;
break;
}
// istanbul ignore else
if (ASSERT_EXISTS(set)) {
return { type: "Set", value: set, complement: complement };
}
// istanbul ignore next
return ASSERT_NEVER_REACH_HERE();
}
protected controlEscapeAtom(): Omit<Character, "loc"> {
let escapeCode;
switch (this.popChar()) {
case "f":
escapeCode = cc("\f");
break;
case "n":
escapeCode = cc("\n");
break;
case "r":
escapeCode = cc("\r");
break;
case "t":
escapeCode = cc("\t");
break;
case "v":
escapeCode = cc("\v");
break;
}
// istanbul ignore else
if (ASSERT_EXISTS(escapeCode)) {
return { type: "Character", value: escapeCode };
}
// istanbul ignore next
return ASSERT_NEVER_REACH_HERE();
}
protected controlLetterEscapeAtom(): Omit<Character, "loc"> {
this.consumeChar("c");
const letter = this.popChar();
if (/[a-zA-Z]/.test(letter) === false) {
throw Error("Invalid ");
}
const letterCode = letter.toUpperCase().charCodeAt(0) - 64;
return { type: "Character", value: letterCode };
}
protected nulCharacterAtom(): Omit<Character, "loc"> {
// TODO implement '[lookahead ∉ DecimalDigit]'
// TODO: for the deprecated octal escape sequence
this.consumeChar("0");
return { type: "Character", value: cc("\0") };
}
protected hexEscapeSequenceAtom(): Omit<Character, "loc"> {
this.consumeChar("x");
return this.parseHexDigits(2);
}
protected regExpUnicodeEscapeSequenceAtom(): Omit<Character, "loc"> {
this.consumeChar("u");
return this.parseHexDigits(4);
}
protected identityEscapeAtom(): Omit<Character, "loc"> {
// TODO: implement "SourceCharacter but not UnicodeIDContinue"
// // http://unicode.org/reports/tr31/#Specific_Character_Adjustments
const escapedChar = this.popChar();
return { type: "Character", value: cc(escapedChar) };
}
protected classPatternCharacterAtom(): Omit<Character, "loc"> {
switch (this.peekChar()) {
// istanbul ignore next
case "\n":
// istanbul ignore next
case "\r":
// istanbul ignore next
case "\u2028":
// istanbul ignore next
case "\u2029":
// istanbul ignore next
case "\\":
// istanbul ignore next
case "]":
throw Error("TBD");
default:
const nextChar = this.popChar();
return { type: "Character", value: cc(nextChar) };
}
}
protected characterClass(): Omit<Set, "loc"> {
const set: (number | Range)[] = [];
let complement = false;
this.consumeChar("[");
if (this.peekChar(0) === "^") {
this.consumeChar("^");
complement = true;
}
while (this.isClassAtom()) {
const from = this.classAtom();
const isFromSingleChar = from.type === "Character";
if (isCharacter(from) && this.isRangeDash()) {
this.consumeChar("-");
const to = this.classAtom();
const isToSingleChar = to.type === "Character";
// a range can only be used when both sides are single characters
if (isCharacter(to)) {
if (to.value < from.value) {
throw Error("Range out of order in character class");
}
set.push({ from: from.value, to: to.value });
} else {
// literal dash
insertToSet(from.value, set);
set.push(cc("-"));
insertToSet(to.value, set);
}
} else {
insertToSet(from.value, set);
}
}
this.consumeChar("]");
return { type: "Set", complement: complement, value: set };
}
protected classAtom(): Omit<Character | Set, "loc"> {
switch (this.peekChar()) {
// istanbul ignore next
case "]":
// istanbul ignore next
case "\n":
// istanbul ignore next
case "\r":
// istanbul ignore next
case "\u2028":
// istanbul ignore next
case "\u2029":
throw Error("TBD");
case "\\":
return this.classEscape();
default:
return this.classPatternCharacterAtom();
}
}
protected classEscape(): Omit<Character | Set, "loc"> {
this.consumeChar("\\");
switch (this.peekChar()) {
// Matches a backspace.
// (Not to be confused with \b word boundary outside characterClass)
case "b":
this.consumeChar("b");
return { type: "Character", value: cc("\u0008") };
case "d":
case "D":
case "s":
case "S":
case "w":
case "W":
return this.characterClassEscape();
case "f":
case "n":
case "r":
case "t":
case "v":
return this.controlEscapeAtom();
case "c":
return this.controlLetterEscapeAtom();
case "0":
return this.nulCharacterAtom();
case "x":
return this.hexEscapeSequenceAtom();
case "u":
return this.regExpUnicodeEscapeSequenceAtom();
default:
return this.identityEscapeAtom();
}
}
protected group(): Omit<Group, "loc"> {
let capturing = true;
this.consumeChar("(");
switch (this.peekChar(0)) {
case "?":
this.consumeChar("?");
this.consumeChar(":");
capturing = false;
break;
default:
this.groupIdx++;
break;
}
const value = this.disjunction();
this.consumeChar(")");
const groupAst: Omit<Group, "loc"> = {
type: "Group",
capturing: capturing,
value: value,
};
if (capturing) {
groupAst["idx"] = this.groupIdx;
}
return groupAst;
}
protected positiveInteger(): number {
let number = this.popChar();
// istanbul ignore next - can't ever get here due to previous lookahead checks
// still implementing this error checking in case this ever changes.
if (decimalPatternNoZero.test(number) === false) {
throw Error("Expecting a positive integer");
}
while (decimalPattern.test(this.peekChar(0))) {
number += this.popChar();
}
return parseInt(number, 10);
}
protected integerIncludingZero(): number {
let number = this.popChar();
if (decimalPattern.test(number) === false) {
throw Error("Expecting an integer");
}
while (decimalPattern.test(this.peekChar(0))) {
number += this.popChar();
}
return parseInt(number, 10);
}
protected patternCharacter(): Omit<Character, "loc"> {
const nextChar = this.popChar();
switch (nextChar) {
// istanbul ignore next
case "\n":
// istanbul ignore next
case "\r":
// istanbul ignore next
case "\u2028":
// istanbul ignore next
case "\u2029":
// istanbul ignore next
case "^":
// istanbul ignore next
case "$":
// istanbul ignore next
case "\\":
// istanbul ignore next
case ".":
// istanbul ignore next
case "*":
// istanbul ignore next
case "+":
// istanbul ignore next
case "?":
// istanbul ignore next
case "(":
// istanbul ignore next
case ")":
// istanbul ignore next
case "[":
// istanbul ignore next
case "|":
// istanbul ignore next
throw Error("TBD");
default:
return { type: "Character", value: cc(nextChar) };
}
}
protected isRegExpFlag(): boolean {
switch (this.peekChar(0)) {
case "g":
case "i":
case "m":
case "u":
case "y":
return true;
default:
return false;
}
}
protected isRangeDash(): boolean {
return this.peekChar() === "-" && this.isClassAtom(1);
}
protected isDigit(): boolean {
return decimalPattern.test(this.peekChar(0));
}
protected isClassAtom(howMuch = 0): boolean {
switch (this.peekChar(howMuch)) {
case "]":
case "\n":
case "\r":
case "\u2028":
case "\u2029":
return false;
default:
return true;
}
}
protected isTerm() {
return this.isAtom() || this.isAssertion();
}
protected isAtom(): boolean {
if (this.isPatternCharacter()) {
return true;
}
switch (this.peekChar(0)) {
case ".":
case "\\": // atomEscape
case "[": // characterClass
// TODO: isAtom must be called before isAssertion - disambiguate
case "(": // group
return true;
default:
return false;
}
}
protected isAssertion(): boolean {
switch (this.peekChar(0)) {
case "^":
case "$":
return true;
// '\b' or '\B'
case "\\":
switch (this.peekChar(1)) {
case "b":
case "B":
return true;
default:
return false;
}
// '(?=' or '(?!' or `(?<=` or `(?<!`
case "(":
return (
this.peekChar(1) === "?" &&
(this.peekChar(2) === "=" ||
this.peekChar(2) === "!" ||
(this.peekChar(2) === "<" &&
(this.peekChar(3) === "=" || this.peekChar(3) === "!")))
);
default:
return false;
}
}
protected isQuantifier(): boolean {
const prevState = this.saveState();
try {
return this.quantifier(true) !== undefined;
} catch (e) {
return false;
} finally {
this.restoreState(prevState);
}
}
protected isPatternCharacter(): boolean {
switch (this.peekChar()) {
case "^":
case "$":
case "\\":
case ".":
case "*":
case "+":
case "?":
case "(":
case ")":
case "[":
case "|":
case "/":
case "\n":
case "\r":
case "\u2028":
case "\u2029":
return false;
default:
return true;
}
}
protected parseHexDigits(howMany: number): Omit<Character, "loc"> {
let hexString = "";
for (let i = 0; i < howMany; i++) {
const hexChar = this.popChar();
if (hexDigitPattern.test(hexChar) === false) {
throw Error("Expecting a HexDecimal digits");
}
hexString += hexChar;
}
const charCode = parseInt(hexString, 16);
return { type: "Character", value: charCode };
}
protected peekChar(howMuch = 0): string {
return this.input[this.idx + howMuch];
}
protected popChar(): string {
const nextChar = this.peekChar(0);
this.consumeChar(undefined);
return nextChar;
}
protected consumeChar(char: string | undefined): void {
if (char !== undefined && this.input[this.idx] !== char) {
throw Error(
"Expected: '" +
char +
"' but found: '" +
this.input[this.idx] +
"' at offset: " +
this.idx,
);
}
if (this.idx >= this.input.length) {
throw Error("Unexpected end of input");
}
this.idx++;
}
protected loc(begin: number): Location {
return { begin: begin, end: this.idx };
}
}
client/node_modules/@chevrotain/regexp-to-ast/src/utils.ts
Generated Vendored
+44
View File
@@ -0,0 +1,44 @@
import type { Character, IRegExpAST, RegExpFlags } from "../types";
export function cc(char: string): number {
return char.charCodeAt(0);
}
export function insertToSet<T>(item: T | T[], set: T[]) {
if (Array.isArray(item)) {
item.forEach(function (subItem) {
set.push(subItem);
});
} else {
set.push(item);
}
}
export function addFlag(
flagObj: RegExpFlags,
flagKey: keyof Omit<RegExpFlags, keyof IRegExpAST>,
) {
if (flagObj[flagKey] === true) {
throw "duplicate flag " + flagKey;
}
const x: boolean = flagObj[flagKey];
flagObj[flagKey] = true;
}
export function ASSERT_EXISTS<T = Object>(obj: any): obj is T {
// istanbul ignore next
if (obj === undefined) {
throw Error("Internal Error - Should never get here!");
}
return true;
}
// istanbul ignore next
export function ASSERT_NEVER_REACH_HERE(): any {
throw Error("Internal Error - Should never get here!");
}
export function isCharacter(obj: { type: string }): obj is Character {
return obj["type"] === "Character";
}
client/node_modules/@chevrotain/regexp-to-ast/types.d.ts
Generated Vendored
+138
View File
@@ -0,0 +1,138 @@
export class RegExpParser {
pattern: (input: string) => RegExpPattern;
}
export interface IRegExpAST {
type: string;
loc: Location;
}
export interface Location {
begin: number;
end: number;
}
export type RegExpAstPart =
| RegExpPattern
| RegExpFlags
| Disjunction
| Alternative
| Atom
| Assertion
| Quantifier;
export interface RegExpPattern extends IRegExpAST {
type: "Pattern";
flags: RegExpFlags;
value: Disjunction;
}
export interface RegExpFlags extends IRegExpAST {
type: "Flags";
global: boolean;
ignoreCase: boolean;
multiLine: boolean;
unicode: boolean;
sticky: boolean;
}
export interface Disjunction extends IRegExpAST {
type: "Disjunction";
value: Alternative[];
}
export interface Alternative extends IRegExpAST {
type: "Alternative";
value: Term[];
}
export type Term = Atom | Assertion;
export interface Assertion extends IRegExpAST {
type:
| "StartAnchor"
| "EndAnchor"
| "WordBoundary"
| "NonWordBoundary"
| "Lookahead"
| "NegativeLookahead"
| "Lookbehind"
| "NegativeLookbehind";
value?: Disjunction;
}
export type Atom = Character | Set | Group | GroupBackReference;
export interface Character extends IRegExpAST {
type: "Character";
value: number;
quantifier?: Quantifier;
}
export type Range = { from: number; to: number };
export interface Set extends IRegExpAST {
type: "Set";
complement: boolean;
value: (number | Range)[];
quantifier?: Quantifier;
}
export interface Group extends IRegExpAST {
type: "Group";
value: Disjunction;
capturing: boolean;
idx?: number;
quantifier?: Quantifier;
}
export interface GroupBackReference extends IRegExpAST {
type: "GroupBackReference";
value: number;
quantifier?: Quantifier;
}
export interface Quantifier extends IRegExpAST {
type: "Quantifier";
atLeast: number;
atMost: number;
greedy: boolean;
}
export class BaseRegExpVisitor {
/**
* The entry point visitor method.
* This will dispatch to the specific visitor method.
*/
visit(node: IRegExpAST): void;
/**
* The entry point for visiting the children of a node.
* Override this to filter the types of children visited
* or to support new types of children in extended ASTs.
*/
visitChildren(node: IRegExpAST): void;
/**
* The specific visitor methods
* Override some of these of create custom visitors.
*/
visitPattern(node: RegExpPattern): void;
visitFlags(node: RegExpFlags): void;
visitDisjunction(node: Disjunction): void;
visitAlternative(node: Alternative): void;
visitStartAnchor(node: Assertion): void;
visitEndAnchor(node: Assertion): void;
visitWordBoundary(node: Assertion): void;
visitNonWordBoundary(node: Assertion): void;
visitLookahead(node: Assertion): void;
visitNegativeLookahead(node: Assertion): void;
visitLookbehind(node: Assertion): void;
visitNegativeLookbehind(node: Assertion): void;
visitCharacter(node: Character): void;
visitSet(node: Set): void;
visitGroup(Node: Group): void;
visitGroupBackReference(Node: GroupBackReference): void;
visitQuantifier(Node: Quantifier): void;
}