?? re.java
字號:
} break; case E_SPACE: case E_NSPACE: if (!(Character.isWhitespace(c) == (opdata == E_SPACE))) { return -1; } break; } idx++; break; default: internalError("Unrecognized escape '" + opdata + "'"); } break; case OP_ANY: if ((matchFlags & MATCH_SINGLELINE) == MATCH_SINGLELINE) { // Match anything if (search.isEnd(idx)) { return -1; } } else { // Match anything but a newline if (search.isEnd(idx) || isNewline(idx)) { return -1; } } idx++; break; case OP_ATOM: { // Match an atom value if (search.isEnd(idx)) { return -1; } // Get length of atom and starting index // int lenAtom = opdata; int startAtom = node + nodeSize; // Give up if not enough input remains to have a match if (search.isEnd(opdata + idx - 1)) { return -1; } // Match atom differently depending on casefolding flag final boolean caseFold = ((matchFlags & MATCH_CASEINDEPENDENT) != 0); for (int i = 0; i < opdata; i++) { if (compareChars(search.charAt(idx++), instruction[startAtom + i], caseFold) != 0) { return -1; } } } break; case OP_POSIXCLASS: { // Out of input? if (search.isEnd(idx)) { return -1; } switch (opdata) { case POSIX_CLASS_ALNUM: if (!Character.isLetterOrDigit(search.charAt(idx))) { return -1; } break; case POSIX_CLASS_ALPHA: if (!Character.isLetter(search.charAt(idx))) { return -1; } break; case POSIX_CLASS_DIGIT: if (!Character.isDigit(search.charAt(idx))) { return -1; } break; case POSIX_CLASS_BLANK: // JWL - bugbug: is this right?? if (!Character.isSpaceChar(search.charAt(idx))) { return -1; } break; case POSIX_CLASS_SPACE: if (!Character.isWhitespace(search.charAt(idx))) { return -1; } break; case POSIX_CLASS_CNTRL: if (Character.getType(search.charAt(idx)) != Character.CONTROL) { return -1; } break; case POSIX_CLASS_GRAPH: // JWL - bugbug??? switch (Character.getType(search.charAt(idx))) { case Character.MATH_SYMBOL: case Character.CURRENCY_SYMBOL: case Character.MODIFIER_SYMBOL: case Character.OTHER_SYMBOL: break; default: return -1; } break; case POSIX_CLASS_LOWER: if (Character.getType(search.charAt(idx)) != Character.LOWERCASE_LETTER) { return -1; } break; case POSIX_CLASS_UPPER: if (Character.getType(search.charAt(idx)) != Character.UPPERCASE_LETTER) { return -1; } break; case POSIX_CLASS_PRINT: if (Character.getType(search.charAt(idx)) == Character.CONTROL) { return -1; } break; case POSIX_CLASS_PUNCT: { int type = Character.getType(search.charAt(idx)); switch(type) { case Character.DASH_PUNCTUATION: case Character.START_PUNCTUATION: case Character.END_PUNCTUATION: case Character.CONNECTOR_PUNCTUATION: case Character.OTHER_PUNCTUATION: break; default: return -1; } } break; case POSIX_CLASS_XDIGIT: // JWL - bugbug?? { boolean isXDigit = ((search.charAt(idx) >= '0' && search.charAt(idx) <= '9') || (search.charAt(idx) >= 'a' && search.charAt(idx) <= 'f') || (search.charAt(idx) >= 'A' && search.charAt(idx) <= 'F')); if (!isXDigit) { return -1; } } break; case POSIX_CLASS_JSTART: if (!Character.isJavaIdentifierStart(search.charAt(idx))) { return -1; } break; case POSIX_CLASS_JPART: if (!Character.isJavaIdentifierPart(search.charAt(idx))) { return -1; } break; default: internalError("Bad posix class"); break; } // Matched. idx++; } break; case OP_ANYOF: { // Out of input? if (search.isEnd(idx)) { return -1; } // Get character to match against character class and maybe casefold char c = search.charAt(idx); boolean caseFold = (matchFlags & MATCH_CASEINDEPENDENT) != 0; // Loop through character class checking our match character int idxRange = node + nodeSize; int idxEnd = idxRange + (opdata * 2); boolean match = false; for (int i = idxRange; !match && i < idxEnd; ) { // Get start, end and match characters char s = instruction[i++]; char e = instruction[i++]; match = ((compareChars(c, s, caseFold) >= 0) && (compareChars(c, e, caseFold) <= 0)); } // Fail if we didn't match the character class if (!match) { return -1; } idx++; } break; case OP_BRANCH: { // Check for choices // FIXME Dead code - only reason to keep is backward compat with pre-compiled exprs. Remove? if (instruction[next /* + offsetOpcode */] != OP_BRANCH) { // If there aren't any other choices, just evaluate this branch. node += nodeSize; continue; } // Try all available branches int nextBranch; do { // Try matching the branch against the string if ((idxNew = matchNodes(node + nodeSize, maxNode, idx)) != -1) { return idxNew; } // Go to next branch (if any) nextBranch = (short) instruction[node + offsetNext]; node += nextBranch; } while (nextBranch != 0 && (instruction[node /* + offsetOpcode */] == OP_BRANCH)); // Failed to match any branch! return -1; } case OP_OPEN_CLUSTER: case OP_CLOSE_CLUSTER: // starting or ending the matching of a subexpression which has no backref. case OP_NOTHING: case OP_GOTO: // Just advance to the next node without doing anything break; case OP_CONTINUE: // Advance to the following node node += nodeSize; continue; case OP_END: // Match has succeeded! setParenEnd(0, idx); return idx; default: // Corrupt program internalError("Invalid opcode '" + opcode + "'"); } // Advance to the next node in the program node = next; } // We "should" never end up here internalError("Corrupt program"); return -1; } /** * Match the current regular expression program against the current * input string, starting at index i of the input string. This method * is only meant for internal use. * * @param i The input string index to start matching at * @return True if the input matched the expression */ protected boolean matchAt(int i) { // Initialize start pointer, paren cache and paren count start0 = -1; end0 = -1; start1 = -1; end1 = -1; start2 = -1; end2 = -1; startn = null; endn = null; parenCount = 1; setParenStart(0, i); // Allocate backref arrays (unless optimizations indicate otherwise) if ((program.flags & REProgram.OPT_HASBACKREFS) != 0) { startBackref = new int[maxParen]; endBackref = new int[maxParen]; } // Match against string int idx; if ((idx = matchNodes(0, maxNode, i)) != -1) { setParenEnd(0, idx); return true; }?? 快捷鍵說明
復制代碼
Ctrl + C
搜索代碼
Ctrl + F
全屏模式
F11
切換主題
Ctrl + Shift + D
顯示快捷鍵
?
增大字號
Ctrl + =
減小字號
Ctrl + -