phoedos/pmd
1
1
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Port python module

Browse Source
This commit is contained in:
Clément Fournier
2020-02-16 21:17:10 +01:00
parent 8ab362c0ad
commit 579c134061
8 changed files with 136 additions and 265 deletions
Download Patch File Download Diff File Expand all files Collapse all files

139
pmd-python/etc/grammar/python.jj → pmd-python/etc/grammar/Python.jj
View File

@ -1,30 +1,30 @@
/**
* This Python 2.7 grammar was copied from the PyDev Project. (http://www.pydev.org/)
*
* Original source file:
* This Python 2.7 grammar was copied from the PyDev Project. (http://www.pydev.org/)
*
* Original source file:
* https://github.com/aptana/Pydev/blob/development/plugins/org.python.pydev.parser/src/org/python/pydev/parser/grammar27/python.jjt (commit 32950d534139f286e03d34795aec99edab09c04c)
*/
options {
BUILD_PARSER=false;
CACHE_TOKENS=true;
STATIC=false;
UNICODE_INPUT = true;
USER_CHAR_STREAM=true;
USER_CHAR_STREAM=true;
}
PARSER_BEGIN(PythonParser)
PARSER_BEGIN(PythonParserImpl)
package net.sourceforge.pmd.lang.python.ast;
import net.sourceforge.pmd.lang.ast.CharStream;
import net.sourceforge.pmd.lang.ast.TokenMgrError;
public class PythonParser {
public class PythonParserImpl {
}
PARSER_END(PythonParser)
PARSER_END(PythonParserImpl)
SKIP :
{
@ -175,110 +175,49 @@ MORE : /* Strings */
| < (["r", "R"])? "\"\"\"" > : IN_STRING23
}
<IN_STRING11> TOKEN : { <SINGLE_STRING: "'"> {
matchedToken.image = image.toString(); } : DEFAULT}
<IN_STRING21> TOKEN : { <SINGLE_STRING2: "\""> {
matchedToken.image = image.toString(); } : DEFAULT}
<IN_STRING13> TOKEN : { <TRIPLE_STRING: "'''"> {
matchedToken.image = image.toString(); } : DEFAULT}
<IN_STRING23> TOKEN : { <TRIPLE_STRING2: "\"\"\""> {
matchedToken.image = image.toString(); } : DEFAULT}
<IN_STRING11> TOKEN : { <SINGLE_STRING: "'"> : DEFAULT}
<IN_STRING21> TOKEN : { <SINGLE_STRING2: "\""> : DEFAULT}
<IN_STRING13> TOKEN : { <TRIPLE_STRING: "'''"> : DEFAULT}
<IN_STRING23> TOKEN : { <TRIPLE_STRING2: "\"\"\""> : DEFAULT}
<IN_BSTRING11> TOKEN : { <SINGLE_BSTRING: "'"> {
matchedToken.image = image.toString(); } : DEFAULT}
<IN_BSTRING21> TOKEN : { <SINGLE_BSTRING2: "\""> {
matchedToken.image = image.toString(); } : DEFAULT}
<IN_BSTRING13> TOKEN : { <TRIPLE_BSTRING: "'''"> {
matchedToken.image = image.toString(); } : DEFAULT}
<IN_BSTRING23> TOKEN : { <TRIPLE_BSTRING2: "\"\"\""> {
matchedToken.image = image.toString(); } : DEFAULT}
<IN_BSTRING11> TOKEN : { <SINGLE_BSTRING: "'"> : DEFAULT}
<IN_BSTRING21> TOKEN : { <SINGLE_BSTRING2: "\""> : DEFAULT}
<IN_BSTRING13> TOKEN : { <TRIPLE_BSTRING: "'''"> : DEFAULT}
<IN_BSTRING23> TOKEN : { <TRIPLE_BSTRING2: "\"\"\"">: DEFAULT}
<IN_USTRING11> TOKEN : { <SINGLE_USTRING: "'"> {
matchedToken.image = image.toString(); } : DEFAULT}
<IN_USTRING21> TOKEN : { <SINGLE_USTRING2: "\""> {
matchedToken.image = image.toString(); } : DEFAULT}
<IN_USTRING13> TOKEN : { <TRIPLE_USTRING: "'''"> {
matchedToken.image = image.toString(); } : DEFAULT}
<IN_USTRING23> TOKEN : { <TRIPLE_USTRING2: "\"\"\""> {
matchedToken.image = image.toString(); } : DEFAULT}
<IN_USTRING11> TOKEN : { <SINGLE_USTRING: "'"> : DEFAULT}
<IN_USTRING21> TOKEN : { <SINGLE_USTRING2: "\""> : DEFAULT}
<IN_USTRING13> TOKEN : { <TRIPLE_USTRING: "'''"> : DEFAULT}
<IN_USTRING23> TOKEN : { <TRIPLE_USTRING2: "\"\"\"">: DEFAULT}
<IN_STRING11> MORE:
{
<"\\\r\n"> { image.setLength(image.length()-3); } : IN_STRING1NLC
| <("\\" ("\n"|"\r"))> { image.setLength(image.length()-2); } : IN_STRING1NLC
<IN_STRING11, IN_USTRING11, IN_BSTRING11> MORE: {
"\\'"
}
<IN_STRING21, IN_USTRING21, IN_BSTRING21> MORE: {
"\\\""
}
<IN_STRING21> MORE:
<IN_STRING11, IN_STRING21,
IN_USTRING11, IN_USTRING21,
IN_BSTRING11, IN_BSTRING21> MORE:
{
<"\\\r\n"> { image.setLength(image.length()-3); } : IN_STRING2NLC
| <("\\" ("\n"|"\r"))> { image.setLength(image.length()-2); } : IN_STRING2NLC
// escaping a newline ignores it, this is handled by the token document
"\\\r\n" | "\\\n" | "\\\r"
| "\\\\"
| < ~["\n","\r"] >
}
<IN_USTRING11> MORE:
{
<"\\\r\n"> { image.setLength(image.length()-3); } : IN_USTRING1NLC
| <("\\" ("\n"|"\r"))> { image.setLength(image.length()-2); } : IN_USTRING1NLC
}
<IN_USTRING21> MORE:
{
<"\\\r\n"> { image.setLength(image.length()-3); } : IN_USTRING2NLC
| <("\\" ("\n"|"\r"))> { image.setLength(image.length()-2); } : IN_USTRING2NLC
}
<IN_BSTRING11> MORE:
{
<"\\\r\n"> { image.setLength(image.length()-3); } : IN_BSTRING1NLC
| <("\\" ("\n"|"\r"))> { image.setLength(image.length()-2); } : IN_BSTRING1NLC
}
<IN_BSTRING21> MORE:
{
<"\\\r\n"> { image.setLength(image.length()-3); } : IN_BSTRING2NLC
| <("\\" ("\n"|"\r"))> { image.setLength(image.length()-2); } : IN_BSTRING2NLC
}
<IN_STRING1NLC> MORE:
{
<""> : IN_STRING11
}
<IN_STRING2NLC> MORE:
{
<""> : IN_STRING21
}
<IN_USTRING1NLC> MORE:
{
<""> : IN_USTRING11
}
<IN_USTRING2NLC> MORE:
{
<""> : IN_USTRING21
}
<IN_BSTRING1NLC> MORE:
{
<""> : IN_BSTRING11
}
<IN_BSTRING2NLC> MORE:
{
<""> : IN_BSTRING21
}
<IN_STRING11, IN_USTRING11, IN_BSTRING11> MORE: { <("\\" ("\\"|"'")) | ~["\n","\r"]> }
<IN_STRING21, IN_USTRING21, IN_BSTRING21> MORE: { <("\\" ("\\"|"\"")) | ~["\n","\r"]> }
// NLs are normalized in triple-quoted strings
<IN_STRING13, IN_STRING23, IN_USTRING13, IN_USTRING23, IN_BSTRING13, IN_BSTRING23> MORE:
{
<"\r\n"> {
"\r\n" {
int l = image.length();
image.setLength(l-1);
image.setCharAt(l-2, '\n');
}
| <"\n">
| <"\r"> { image.setCharAt(image.length()-1, '\n'); }
| <~["\n","\r"]>
| <"\\" ~["\n","\r"]>
| "\n"
| "\r" { image.setCharAt(image.length()-1, '\n'); }
| < ~["\n","\r"] >
| < "\\" ~["\n","\r"] >
}