From 4d39507183e0ace2d73f04817a398e858b66b677 Mon Sep 17 00:00:00 2001
From: Jan Breuer <jan.breuer@jaybee.cz>
Date: 周五, 22 3月 2013 01:40:22 +0800
Subject: [PATCH] Update lexer, start of implementing parser
---
libscpi/src/utils.c | 328 ++++++++++++++++++++++++++++++++++--------------------
1 files changed, 206 insertions(+), 122 deletions(-)
diff --git a/libscpi/src/utils.c b/libscpi/src/utils.c
index 9f9e2e7..8880636 100644
--- a/libscpi/src/utils.c
+++ b/libscpi/src/utils.c
@@ -147,152 +147,214 @@
return FALSE;
}
- if (strncasecmp(str1, str2, len2) == 0) {
+ if (SCPI_strncasecmp(str1, str2, len2) == 0) {
return TRUE;
}
return FALSE;
}
-bool_t locateText(const char * str1, size_t len1, char ** str2, size_t * len2) {
+enum _locate_text_states {
+ STATE_FIRST_WHITESPACE,
+ STATE_TEXT_QUOTED,
+ STATE_TEXT,
+ STATE_LAST_WHITESPACE,
+ STATE_COMMA,
+ STATE_ERROR
+};
+typedef enum _locate_text_states locate_text_states;
+
+struct _locate_text_nfa {
+ locate_text_states state;
+ int32_t startIdx;
+ int32_t stopIdx;
size_t i;
- int quot = 0;
- int32_t strStart = -1;
- int32_t strStop = -1;
- int valid = 0;
+};
+typedef struct _locate_text_nfa locate_text_nfa;
-
- for (i = 0; i < len1; i++) {
- if ((strStart < 0) && isspace(str1[i])) {
- continue;
- }
-
- if ((strStart < 0) && !quot && (str1[i] == '"')) {
- quot = 1;
- continue;
- }
-
- if (strStart < 0) {
- strStart = i;
- }
-
- if ((strStop < 0) && quot && (str1[i] == '"')) {
- strStop = i;
- valid = 1;
- continue;
- }
-
- if ((strStop >= 0) && quot && (str1[i] == ',')) {
- break;
- }
-
- if ((strStop >= 0) && quot && !isspace(str1[i])) {
- valid = 0;
- }
-
- if (!quot && !isspace(str1[i]) && (str1[i] != ',')) {
- strStop = i;
- }
-
- if (isspace(str1[i])) {
- continue;
- }
-
- if ((strStop >= 0) && (str1[i] == ',')) {
- valid = 1;
- break;
- }
- }
-
- if ((i == len1) && !quot) {
- valid = 1;
- if (strStop < 0) {
- strStop = i;
- } else {
- strStop++;
- }
- if (strStart < 0) {
- strStart = i;
- }
- } else if (!quot) {
- strStop++;
- }
-
-
- if (valid) {
- if (str2) {
- *str2 = (char *) &str1[strStart];
- }
-
- if (len2) {
- *len2 = strStop - strStart;
- }
- }
-
- return valid;
+/**
+ * Test locate text state, if it is correct final state
+ */
+static bool_t isFinalState(locate_text_states state) {
+ return (
+ ((state) == STATE_COMMA)
+ || ((state) == STATE_LAST_WHITESPACE)
+ || ((state) == STATE_TEXT) ||
+ ((state) == STATE_FIRST_WHITESPACE)
+ );
}
-bool_t locateStr(const char * str1, size_t len1, char ** str2, size_t * len2) {
- size_t i;
- int32_t strStart = -1;
- int32_t strStop = -1;
- int valid = 0;
-
-
- for (i = 0; i < len1; i++) {
- if ((strStart < 0) && isspace(str1[i])) {
- continue;
- }
-
- if (strStart < 0) {
- strStart = i;
- }
-
- if (!isspace(str1[i]) && (str1[i] != ',')) {
- strStop = i;
- }
-
- if (isspace(str1[i])) {
- continue;
- }
-
- if (str1[i] == ',') {
- valid = 1;
-
- if (strStop < 0) {
- strStop = i;
+/**
+ * Perform locateText automaton to search string pattern
+ * @param nfa stores automaton state
+ * @param c current char processed
+ */
+static bool_t locateTextAutomaton(locate_text_nfa * nfa, unsigned char c) {
+ switch(nfa->state) {
+ /* first state locating only white spaces */
+ case STATE_FIRST_WHITESPACE:
+ if(isspace(c)) {
+ nfa->startIdx = nfa->stopIdx = nfa->i + 1;
+ } else if (c == ',') {
+ nfa->state = STATE_COMMA;
+ } else if (c == '"') {
+ nfa->startIdx = nfa->i + 1;
+ nfa->state = STATE_TEXT_QUOTED;
+ } else {
+ nfa->startIdx = nfa->i;
+ nfa->stopIdx = nfa->i + 1;
+ nfa->state = STATE_TEXT;
}
break;
- }
+ /* state locating any text inside "" */
+ case STATE_TEXT_QUOTED:
+ if(c == '"') {
+ nfa->state = STATE_LAST_WHITESPACE;
+ nfa->stopIdx = nfa->i;
+ }
+ break;
+ /* locate text ignoring quotes */
+ case STATE_TEXT:
+ if (c == ',') {
+ nfa->state = STATE_COMMA;
+ } else if (!isspace(c)) {
+ nfa->stopIdx = nfa->i + 1;
+ }
+ break;
+ /* locating text after last quote */
+ case STATE_LAST_WHITESPACE:
+ if (c == ',') {
+ nfa->state = STATE_COMMA;
+ } else if (!isspace(c)) {
+ nfa->state = STATE_ERROR;
+ }
+ break;
+
+ default:
+ break;
}
- if (i == len1) {
- valid = 1;
- if (strStop < 0) {
- strStop = i;
- } else {
- strStop++;
- }
- if (strStart < 0) {
- strStart = i;
- }
+ /* if it is terminating state, break from for loop */
+ if ((nfa->state == STATE_COMMA) || (nfa->state == STATE_ERROR)) {
+ return FALSE;
} else {
- strStop++;
+ return TRUE;
+ }
+}
+
+/**
+ * Locate text in string. Text is separated by two ""
+ * example: "text", next parameter
+ * regexp: ^[ \t\r\n]*"([^"]*)"[ \t\r\n]*,?
+ * regexp: ^[ \t\r\n]*([^,]*)[ \t\r\n]*,?
+ * @param str1 string to be searched
+ * @param len1 length of string
+ * @param str2 result
+ * @param len2 length of result
+ * @return string str1 contains text and str2 was set
+ */
+bool_t locateText(const char * str1, size_t len1, const char ** str2, size_t * len2) {
+ locate_text_nfa nfa;
+ nfa.state = STATE_FIRST_WHITESPACE;
+ nfa.startIdx = 0;
+ nfa.stopIdx = 0;
+
+ for (nfa.i = 0; nfa.i < len1; nfa.i++) {
+ if(FALSE == locateTextAutomaton(&nfa, str1[nfa.i])) {
+ break;
+ }
}
+ if (isFinalState(nfa.state)) {
- if (valid) {
if (str2) {
- *str2 = (char *) &str1[strStart];
+ *str2 = &str1[nfa.startIdx];
}
if (len2) {
- *len2 = strStop - strStart;
+ *len2 = nfa.stopIdx - nfa.startIdx;
+ }
+ return TRUE;
+ }
+ return FALSE;
+}
+
+/**
+ * Perform locateStr automaton to search string pattern
+ * @param nfa stores automaton state
+ * @param c current char processed
+ */
+static bool_t locateStrAutomaton(locate_text_nfa * nfa, unsigned char c) {
+ switch(nfa->state) {
+ /* first state locating only white spaces */
+ case STATE_FIRST_WHITESPACE:
+ if(isspace(c)) {
+ nfa->startIdx = nfa->stopIdx = nfa->i + 1;
+ } else if (c == ',') {
+ nfa->state = STATE_COMMA;
+ } else {
+ nfa->startIdx = nfa->i;
+ nfa->stopIdx = nfa->i + 1;
+ nfa->state = STATE_TEXT;
+ }
+ break;
+ /* locate text ignoring quotes */
+ case STATE_TEXT:
+ if (c == ',') {
+ nfa->state = STATE_COMMA;
+ } else if (!isspace(c)) {
+ nfa->stopIdx = nfa->i + 1;
+ }
+ break;
+
+ default:
+ break;
+ }
+
+ /* if it is terminating state, break from for loop */
+ if ((nfa->state == STATE_COMMA) || (nfa->state == STATE_ERROR)) {
+ return FALSE;
+ } else {
+ return TRUE;
+ }
+}
+
+/**
+ * Locate string in string.
+ * regexp: ^[ \t\r\n]*([^,]*)[ \t\r\n]*,?
+ * @param str1 string to be searched
+ * @param len1 length of string
+ * @param str2 result
+ * @param len2 length of result
+ * @return string str1 contains text and str2 was set
+ */
+bool_t locateStr(const char * str1, size_t len1, const char ** str2, size_t * len2) {
+ locate_text_nfa nfa;
+ nfa.state = STATE_FIRST_WHITESPACE;
+ nfa.startIdx = 0;
+ nfa.stopIdx = 0;
+
+
+ for (nfa.i = 0; nfa.i < len1; nfa.i++) {
+ if(FALSE == locateStrAutomaton(&nfa, str1[nfa.i])) {
+ break;
}
}
- return valid;
+ if (isFinalState(nfa.state)) {
+
+ if (str2) {
+ *str2 = &str1[nfa.startIdx];
+ }
+
+ if (len2) {
+ *len2 = nfa.stopIdx - nfa.startIdx;
+ }
+ return TRUE;
+ }
+ return FALSE;
}
+
/**
* Count white spaces from the beggining
@@ -303,7 +365,7 @@
size_t skipWhitespace(const char * cmd, size_t len) {
size_t i;
for (i = 0; i < len; i++) {
- if (!isspace(cmd[i])) {
+ if (!isspace((unsigned char)cmd[i])) {
return i;
}
}
@@ -321,7 +383,7 @@
size_t patternSeparatorShortPos(const char * pattern, size_t len) {
size_t i;
for (i = 0; (i < len) && pattern[i]; i++) {
- if (islower(pattern[i])) {
+ if (islower((unsigned char)pattern[i])) {
return i;
}
}
@@ -341,3 +403,25 @@
return compareStr(pattern, pattern_len, str, str_len) ||
compareStr(pattern, pattern_sep_pos_short, str, str_len);
}
+
+
+#if !HAVE_STRNLEN
+/* use FreeBSD strnlen */
+
+/*-
+ * Copyright (c) 2009 David Schultz <das@FreeBSD.org>
+ * All rights reserved.
+ */
+size_t
+BSD_strnlen(const char *s, size_t maxlen)
+{
+ size_t len;
+
+ for (len = 0; len < maxlen; len++, s++) {
+ if (!*s)
+ break;
+ }
+ return (len);
+}
+#endif
+
--
Gitblit v1.9.1