static PyObject *
Reader_iternext(ReaderObj *self)
{
PyObject *fields = NULL;
Py_UCS4 c;
Py_ssize_t pos, linelen;
unsigned int kind;
void *data;
PyObject *lineobj;
if (parse_reset(self) < 0)
return NULL;
do {
lineobj = PyIter_Next(self->input_iter);
if (lineobj == NULL) {
/* End of input OR exception */
if (!PyErr_Occurred() && self->field_len != 0)
PyErr_Format(error_obj,
"newline inside string");
return NULL;
}
if (!PyUnicode_Check(lineobj)) {
PyErr_Format(error_obj,
"iterator should return strings, "
"not %.200s "
"(did you open the file in text mode?)",
lineobj->ob_type->tp_name
);
Py_DECREF(lineobj);
return NULL;
}
++self->line_num;
kind = PyUnicode_KIND(lineobj);
data = PyUnicode_DATA(lineobj);
pos = 0;
linelen = PyUnicode_GET_LENGTH(lineobj);
while (linelen--) {
c = PyUnicode_READ(kind, data, pos);
if (c == '\0') {
Py_DECREF(lineobj);
PyErr_Format(error_obj,
"line contains NULL byte");
goto err;
}
if (parse_process_char(self, c) < 0) {
Py_DECREF(lineobj);
goto err;
}
pos++;
}
Py_DECREF(lineobj);
if (parse_process_char(self, 0) < 0)
goto err;
} while (self->state != START_RECORD);
fields = self->fields;
self->fields = NULL;
err:
return fields;
}
bool add_entry(char *lbuf, int length, struct dict_entry_t *entry)
{
char *cp;
if (length == 0)
return false;
/* allocate line buffer */
entry->lbuf = (char *) ecalloc(1, length + 1);
strncpy(entry->lbuf, lbuf, length);
/* format: keyword TAB candidate1 TAB candidate2 TAB candidate3... TAB */
if ((cp = strchr(entry->lbuf, '\t')) == NULL)
goto error;
*cp = '\0';
entry->keyword = entry->lbuf;
parse_reset(&entry->candidate);
parse_arg(cp + 1, &entry->candidate, '\t', not_tab);
/* illegal entry */
if (entry->candidate.argc <= 0)
goto error;
return true;
error:
free(entry->lbuf);
return false;
}
static PyObject *
CSVParser_fread(CSVParser *self, size_t size)
{
char *buf = PyMem_Malloc(sizeof(char)*size);
if(buf==NULL){
PyErr_NoMemory();
return NULL;
}
char c;
size_t readsize;
PyObject *datas = PyList_New(0);
if(self->fields==NULL){
parse_reset(self);
}
while(size){
PyFile_IncUseCount((PyFileObject*)self->pyfile);
Py_BEGIN_ALLOW_THREADS
readsize = fread(buf, 1, size, self->file);
Py_END_ALLOW_THREADS
PyFile_DecUseCount((PyFileObject*)self->pyfile);
if(readsize==0)
break;
size -= readsize;
while(readsize--) {
logq_readc(buf)
}
}
err:
return datas;
}
static PyObject *
CSVParser_iternext(CSVParser *self)
{
if(!self->is_file)
return CSVParser_iternext_filelike(self);
char buf[MAXBUFSIZE];
char c;
char *cp;
PyObject *fields = NULL;
long i;
long linelen;
Logq_Engine_reset(self->engine);
while(!self->engine->is_success){
if (parse_reset(self) < 0)
return NULL;
do {
PyFile_IncUseCount((PyFileObject*)self->pyfile);
Py_BEGIN_ALLOW_THREADS
cp = fgets(buf, MAXBUFSIZE, self->file);
Py_END_ALLOW_THREADS
PyFile_DecUseCount((PyFileObject*)self->pyfile);
if (cp == NULL) {
/* End of input OR exception */
if (!PyErr_Occurred() && (self->field_len != 0 ||
self->state == IN_QUOTED_FIELD)) {
if (parse_save_field(self) >= 0 )
break;
}
return NULL;
}
++self->line_num;
linelen = strlen(buf);
if (buf == NULL || linelen < 0) {
return NULL;
}
for(i=0; i<linelen; ++i){
c = buf[i];
if (c == '\0') {
PyErr_Format(csv_error_obj,
"line contains NULL byte");
goto err;
}
if (parse_process_char(self, c) < 0) {
goto err;
}
//query fail. go next line
if (self->state == QUERY_FAIL){
if(buf[linelen-1]=='\n'){
self->state = START_RECORD;
}
break;
}
}
} while (self->state != START_RECORD);
}
fields = self->fields;
self->fields = NULL;
err:
return fields;
}
static PyObject *
CSVParser_iternext_filelike(CSVParser *self)
{
char *buf;
char c;
PyObject *fields = NULL;
PyObject *lineobj = NULL;
long i;
long linelen;
Logq_Engine_reset(self->engine);
while(!self->engine->is_success){
if (parse_reset(self) < 0)
return NULL;
do {
lineobj = PyIter_Next(self->pyfile);
if (lineobj == NULL) {
/* End of input OR exception */
if (!PyErr_Occurred() && (self->field_len != 0 ||
self->state == IN_QUOTED_FIELD)) {
if (parse_save_field(self) >= 0 )
break;
}
return NULL;
}
++self->line_num;
buf = PyString_AsString(lineobj);
linelen = PyString_Size(lineobj);
if (buf == NULL || linelen < 0) {
return NULL;
}
for(i=0; i<linelen; ++i){
c = buf[i];
if (c == '\0') {
Py_DECREF(lineobj);
PyErr_Format(csv_error_obj,
"line contains NULL byte");
goto err;
}
if (parse_process_char(self, c) < 0) {
Py_DECREF(lineobj);
goto err;
}
//query fail. go next line
if (self->state == QUERY_FAIL){
if(buf[linelen-1]=='\n'){
self->state = START_RECORD;
}
break;
}
}
Py_DECREF(lineobj);
} while (self->state != START_RECORD);
}
fields = self->fields;
self->fields = NULL;
err:
return fields;
}
static PyObject *
Reader_iternext(ReaderObj *self)
{
PyObject *lineobj;
PyObject *fields = NULL;
Py_UNICODE *line, c;
Py_ssize_t linelen;
if (parse_reset(self) < 0)
return NULL;
do {
lineobj = PyIter_Next(self->input_iter);
if (lineobj == NULL) {
/* End of input OR exception */
if (!PyErr_Occurred() && self->field_len != 0)
PyErr_Format(error_obj,
"newline inside string");
return NULL;
}
if (!PyUnicode_Check(lineobj)) {
PyErr_Format(error_obj,
"iterator should return strings, "
"not %.200s "
"(did you open the file in text mode?)",
lineobj->ob_type->tp_name
);
Py_DECREF(lineobj);
return NULL;
}
++self->line_num;
line = PyUnicode_AsUnicode(lineobj);
linelen = PyUnicode_GetSize(lineobj);
if (line == NULL || linelen < 0) {
Py_DECREF(lineobj);
return NULL;
}
while (linelen--) {
c = *line++;
if (c == '\0') {
Py_DECREF(lineobj);
PyErr_Format(error_obj,
"line contains NULL byte");
goto err;
}
if (parse_process_char(self, c) < 0) {
Py_DECREF(lineobj);
goto err;
}
}
Py_DECREF(lineobj);
if (parse_process_char(self, 0) < 0)
goto err;
} while (self->state != START_RECORD);
fields = self->fields;
self->fields = NULL;
err:
return fields;
}
static PyObject *
Reader_iternext(ReaderObj *self)
{
PyObject *lineobj;
PyObject *fields = NULL;
char *line, c;
int linelen;
if (parse_reset(self) < 0)
return NULL;
do {
lineobj = PyIter_Next(self->input_iter);
if (lineobj == NULL) {
/* End of input OR exception */
if (!PyErr_Occurred() && (self->field_len != 0 ||
self->state == IN_QUOTED_FIELD)) {
if (self->dialect->strict)
PyErr_SetString(error_obj, "unexpected end of data");
else if (parse_save_field(self) >= 0 )
break;
}
return NULL;
}
++self->line_num;
line = PyString_AsString(lineobj);
linelen = PyString_Size(lineobj);
if (line == NULL || linelen < 0) {
Py_DECREF(lineobj);
return NULL;
}
while (linelen--) {
c = *line++;
if (c == '\0') {
Py_DECREF(lineobj);
PyErr_Format(error_obj,
"line contains NULL byte");
goto err;
}
if (parse_process_char(self, c) < 0) {
Py_DECREF(lineobj);
goto err;
}
}
Py_DECREF(lineobj);
if (parse_process_char(self, 0) < 0)
goto err;
} while (self->state != START_RECORD);
fields = self->fields;
self->fields = NULL;
err:
return fields;
}
bool
window_part::parse(const char* str)
{
const char* p = str;
m_index.clear();
parse_element(p);
bool success = (*p == 0);
if (!success)
parse_reset();
split();
return success;
}
static PyObject *
Reader_iternext(ReaderObj *self)
{
PyObject *lineobj;
PyObject *fields = NULL;
char *line, c;
int linelen;
if (parse_reset(self) < 0)
return NULL;
do {
lineobj = PyIter_Next(self->input_iter);
if (lineobj == NULL) {
/* End of input OR exception */
if (!PyErr_Occurred() && self->field_len != 0)
PyErr_Format(error_obj,
"newline inside string");
return NULL;
}
++self->line_num;
line = PyString_AsString(lineobj);
linelen = PyString_Size(lineobj);
if (line == NULL || linelen < 0) {
Py_DECREF(lineobj);
return NULL;
}
while (linelen--) {
c = *line++;
if (c == '\0') {
Py_DECREF(lineobj);
PyErr_Format(error_obj,
"line contains NULL byte");
goto err;
}
if (parse_process_char(self, c) < 0) {
Py_DECREF(lineobj);
goto err;
}
}
Py_DECREF(lineobj);
if (parse_process_char(self, 0) < 0)
goto err;
} while (self->state != START_RECORD);
fields = self->fields;
self->fields = NULL;
err:
return fields;
}
static PyObject *
csv_reader(PyObject *module, PyObject *args, PyObject *keyword_args)
{
PyObject * iterator, * dialect = NULL;
ReaderObj * self = PyObject_GC_New(ReaderObj, &Reader_Type);
if (!self)
return NULL;
self->dialect = NULL;
self->fields = NULL;
self->input_iter = NULL;
self->field = NULL;
self->field_size = 0;
self->line_num = 0;
if (parse_reset(self) < 0) {
Py_DECREF(self);
return NULL;
}
if (!PyArg_UnpackTuple(args, "", 1, 2, &iterator, &dialect)) {
Py_DECREF(self);
return NULL;
}
self->input_iter = PyObject_GetIter(iterator);
if (self->input_iter == NULL) {
PyErr_SetString(PyExc_TypeError,
"argument 1 must be an iterator");
Py_DECREF(self);
return NULL;
}
self->dialect = (DialectObj *)_call_dialect(dialect, keyword_args);
if (self->dialect == NULL) {
Py_DECREF(self);
return NULL;
}
PyObject_GC_Track(self);
return (PyObject *)self;
}
window_part::window_part()
{
parse_reset();
split();
}
int assemble(struct membuf *source, struct membuf *dest)
{
struct vec guesses_history[1];
struct map guesses_storage[1];
int dest_pos;
int result;
dump_sym_table(LOG_DEBUG, s->initial_symbols);
vec_init(guesses_history, sizeof(struct map));
s->guesses = NULL;
dest_pos = membuf_memlen(dest);
for(;;)
{
map_put_all(s->sym_table, s->initial_symbols);
named_buffer_copy(s->named_buffer, s->initial_named_buffer);
map_init(guesses_storage);
if(s->guesses != NULL)
{
/* copy updated guesses from latest pass */
map_put_all(guesses_storage, s->guesses);
}
s->guesses = guesses_storage;
result = assembleSinglePass(source, dest);
if(result != 0)
{
/* the assemble pass failed */
break;
}
/* check if any guessed symbols was wrong and update them
* to their actual value */
if(wasFinalPass())
{
/* The assemble pass succeeded without any wrong guesses,
* we're done */
break;
}
if(loopDetect(guesses_history))
{
/* More passes would only get us into a loop */
LOG(LOG_VERBOSE, ("Aborting due to loop.\n"));
result = -1;
break;
}
LOG(LOG_VERBOSE, ("Trying another pass.\n"));
/* allocate storage for the guesses in the history vector */
s->guesses = vec_push(guesses_history, s->guesses);
parse_reset();
membuf_truncate(dest, dest_pos);
}
map_free(guesses_storage);
vec_free(guesses_history, (cb_free*)map_free);
s->guesses = NULL;
return result;
}
static PyObject *
CSVParser_new(PyTypeObject *type, PyObject *args, PyObject *kwargs)
{
Engine *engine;
PyObject *pyfile = NULL;
PyObject *map = NULL;
ColMap *colmap = NULL;
char delimiter = ',';
char quotechar = '"';
CSVParser * self = PyObject_GC_New(CSVParser, &CSVParser_Type);
if (self == NULL){
return NULL;
}
if (!PyArg_ParseTupleAndKeywords(args, kwargs,
"O!OO|cc", parser_kws,
&Logq_Engine_Type, &engine,
&pyfile,
&map,
&delimiter, "echar)){
return NULL;
}
Py_INCREF(pyfile);
Py_INCREF(engine);
self->engine = engine;
if(PyFile_Check(pyfile)){
self->file = PyFile_AsFile(pyfile);
self->is_file = 1;
self->pyfile = pyfile;
}else{
self->file = NULL;
self->is_file = 0;
self->pyfile = PyObject_GetIter(pyfile);
if (self->pyfile == NULL) {
PyErr_SetString(PyExc_TypeError,
"argument 1 must be an iterator");
return NULL;
}
}
if(!PySequence_Check(map)){
PyErr_SetString(PyExc_TypeError,
"argument 2 must be a list");
return NULL;
}
colmap = ColMap_new(map);
if (colmap == NULL) {
PyErr_SetString(PyExc_TypeError,
"argument 2 must be a list");
return NULL;
}
self->colmap = colmap;
self->fields = NULL;
self->field = NULL;
self->field_size = 0;
self->line_num = 0;
self->delimiter = delimiter;
self->quotechar = quotechar;
if (parse_reset(self) < 0) {
Py_DECREF(pyfile);
Py_DECREF(engine);
Py_DECREF(self);
return NULL;
}
PyObject_GC_Track(self);
return (PyObject *)self;
}
