csv parser

3 files changed, 253 insertions, 0 deletions

diff --git a/examples/Makefile.am b/examples/Makefile.am
new file mode 100644
index 0000000..c643694
--- /dev/null
+++ b/examples/Makefile.am
@@ -0,0 +1,7 @@
+AM_CPPFLAGS = -I$(top_srcdir)/src
+
+bin_PROGRAMS = parser
+
+parser_SOURCES = ../src/csv_parser.c \
+                 ../src/csv_parser.h \
+                 parser.c
diff --git a/examples/iris.csv b/examples/iris.csv
new file mode 100644
index 0000000..0dba57c
--- /dev/null
+++ b/examples/iris.csv
@@ -0,0 +1,151 @@
+sepalLength,sepalWidth,petalLength,petalWidth,species
+5.1,3.5,1.4,0.2,setosa
+4.9,3.0,1.4,0.2,setosa
+4.7,3.2,1.3,0.2,setosa
+4.6,3.1,1.5,0.2,setosa
+5.0,3.6,1.4,0.2,setosa
+5.4,3.9,1.7,0.4,setosa
+4.6,3.4,1.4,0.3,setosa
+5.0,3.4,1.5,0.2,setosa
+4.4,2.9,1.4,0.2,setosa
+4.9,3.1,1.5,0.1,setosa
+5.4,3.7,1.5,0.2,setosa
+4.8,3.4,1.6,0.2,setosa
+4.8,3.0,1.4,0.1,setosa
+4.3,3.0,1.1,0.1,setosa
+5.8,4.0,1.2,0.2,setosa
+5.7,4.4,1.5,0.4,setosa
+5.4,3.9,1.3,0.4,setosa
+5.1,3.5,1.4,0.3,setosa
+5.7,3.8,1.7,0.3,setosa
+5.1,3.8,1.5,0.3,setosa
+5.4,3.4,1.7,0.2,setosa
+5.1,3.7,1.5,0.4,setosa
+4.6,3.6,1.0,0.2,setosa
+5.1,3.3,1.7,0.5,setosa
+4.8,3.4,1.9,0.2,setosa
+5.0,3.0,1.6,0.2,setosa
+5.0,3.4,1.6,0.4,setosa
+5.2,3.5,1.5,0.2,setosa
+5.2,3.4,1.4,0.2,setosa
+4.7,3.2,1.6,0.2,setosa
+4.8,3.1,1.6,0.2,setosa
+5.4,3.4,1.5,0.4,setosa
+5.2,4.1,1.5,0.1,setosa
+5.5,4.2,1.4,0.2,setosa
+4.9,3.1,1.5,0.1,setosa
+5.0,3.2,1.2,0.2,setosa
+5.5,3.5,1.3,0.2,setosa
+4.9,3.1,1.5,0.1,setosa
+4.4,3.0,1.3,0.2,setosa
+5.1,3.4,1.5,0.2,setosa
+5.0,3.5,1.3,0.3,setosa
+4.5,2.3,1.3,0.3,setosa
+4.4,3.2,1.3,0.2,setosa
+5.0,3.5,1.6,0.6,setosa
+5.1,3.8,1.9,0.4,setosa
+4.8,3.0,1.4,0.3,setosa
+5.1,3.8,1.6,0.2,setosa
+4.6,3.2,1.4,0.2,setosa
+5.3,3.7,1.5,0.2,setosa
+5.0,3.3,1.4,0.2,setosa
+7.0,3.2,4.7,1.4,versicolor
+6.4,3.2,4.5,1.5,versicolor
+6.9,3.1,4.9,1.5,versicolor
+5.5,2.3,4.0,1.3,versicolor
+6.5,2.8,4.6,1.5,versicolor
+5.7,2.8,4.5,1.3,versicolor
+6.3,3.3,4.7,1.6,versicolor
+4.9,2.4,3.3,1.0,versicolor
+6.6,2.9,4.6,1.3,versicolor
+5.2,2.7,3.9,1.4,versicolor
+5.0,2.0,3.5,1.0,versicolor
+5.9,3.0,4.2,1.5,versicolor
+6.0,2.2,4.0,1.0,versicolor
+6.1,2.9,4.7,1.4,versicolor
+5.6,2.9,3.6,1.3,versicolor
+6.7,3.1,4.4,1.4,versicolor
+5.6,3.0,4.5,1.5,versicolor
+5.8,2.7,4.1,1.0,versicolor
+6.2,2.2,4.5,1.5,versicolor
+5.6,2.5,3.9,1.1,versicolor
+5.9,3.2,4.8,1.8,versicolor
+6.1,2.8,4.0,1.3,versicolor
+6.3,2.5,4.9,1.5,versicolor
+6.1,2.8,4.7,1.2,versicolor
+6.4,2.9,4.3,1.3,versicolor
+6.6,3.0,4.4,1.4,versicolor
+6.8,2.8,4.8,1.4,versicolor
+6.7,3.0,5.0,1.7,versicolor
+6.0,2.9,4.5,1.5,versicolor
+5.7,2.6,3.5,1.0,versicolor
+5.5,2.4,3.8,1.1,versicolor
+5.5,2.4,3.7,1.0,versicolor
+5.8,2.7,3.9,1.2,versicolor
+6.0,2.7,5.1,1.6,versicolor
+5.4,3.0,4.5,1.5,versicolor
+6.0,3.4,4.5,1.6,versicolor
+6.7,3.1,4.7,1.5,versicolor
+6.3,2.3,4.4,1.3,versicolor
+5.6,3.0,4.1,1.3,versicolor
+5.5,2.5,4.0,1.3,versicolor
+5.5,2.6,4.4,1.2,versicolor
+6.1,3.0,4.6,1.4,versicolor
+5.8,2.6,4.0,1.2,versicolor
+5.0,2.3,3.3,1.0,versicolor
+5.6,2.7,4.2,1.3,versicolor
+5.7,3.0,4.2,1.2,versicolor
+5.7,2.9,4.2,1.3,versicolor
+6.2,2.9,4.3,1.3,versicolor
+5.1,2.5,3.0,1.1,versicolor
+5.7,2.8,4.1,1.3,versicolor
+6.3,3.3,6.0,2.5,virginica
+5.8,2.7,5.1,1.9,virginica
+7.1,3.0,5.9,2.1,virginica
+6.3,2.9,5.6,1.8,virginica
+6.5,3.0,5.8,2.2,virginica
+7.6,3.0,6.6,2.1,virginica
+4.9,2.5,4.5,1.7,virginica
+7.3,2.9,6.3,1.8,virginica
+6.7,2.5,5.8,1.8,virginica
+7.2,3.6,6.1,2.5,virginica
+6.5,3.2,5.1,2.0,virginica
+6.4,2.7,5.3,1.9,virginica
+6.8,3.0,5.5,2.1,virginica
+5.7,2.5,5.0,2.0,virginica
+5.8,2.8,5.1,2.4,virginica
+6.4,3.2,5.3,2.3,virginica
+6.5,3.0,5.5,1.8,virginica
+7.7,3.8,6.7,2.2,virginica
+7.7,2.6,6.9,2.3,virginica
+6.0,2.2,5.0,1.5,virginica
+6.9,3.2,5.7,2.3,virginica
+5.6,2.8,4.9,2.0,virginica
+7.7,2.8,6.7,2.0,virginica
+6.3,2.7,4.9,1.8,virginica
+6.7,3.3,5.7,2.1,virginica
+7.2,3.2,6.0,1.8,virginica
+6.2,2.8,4.8,1.8,virginica
+6.1,3.0,4.9,1.8,virginica
+6.4,2.8,5.6,2.1,virginica
+7.2,3.0,5.8,1.6,virginica
+7.4,2.8,6.1,1.9,virginica
+7.9,3.8,6.4,2.0,virginica
+6.4,2.8,5.6,2.2,virginica
+6.3,2.8,5.1,1.5,virginica
+6.1,2.6,5.6,1.4,virginica
+7.7,3.0,6.1,2.3,virginica
+6.3,3.4,5.6,2.4,virginica
+6.4,3.1,5.5,1.8,virginica
+6.0,3.0,4.8,1.8,virginica
+6.9,3.1,5.4,2.1,virginica
+6.7,3.1,5.6,2.4,virginica
+6.9,3.1,5.1,2.3,virginica
+5.8,2.7,5.1,1.9,virginica
+6.8,3.2,5.9,2.3,virginica
+6.7,3.3,5.7,2.5,virginica
+6.7,3.0,5.2,2.3,virginica
+6.3,2.5,5.0,1.9,virginica
+6.5,3.0,5.2,2.0,virginica
+6.2,3.4,5.4,2.3,virginica
+5.9,3.0,5.1,1.8,virginica
diff --git a/examples/parser.c b/examples/parser.c
new file mode 100644
index 0000000..50c30d6
--- /dev/null
+++ b/examples/parser.c
@@ -0,0 +1,95 @@
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <fcntl.h>
+#include <csv_parser.h>
+
+
+typedef struct field_ {
+    char data[32];
+    int row;
+    int col;
+    struct field_ *next;
+} field_t;
+
+
+typedef struct csv_ {
+    field_t *head;
+    field_t *tail;
+} csv_t;
+
+
+field_t *new_field(const char *data, size_t length, int row, int col)
+{
+    field_t *field = malloc(sizeof(field_t));
+    memset(field, 0, sizeof(field_t));
+    field->row = row;
+    field->col = col;
+    strncpy(field->data, data, length);
+    return field;
+}
+
+
+int field_cb(csv_parser_t *parser, const char *data, size_t length, int row, int col)
+{
+    csv_t *csv = parser->data;
+    field_t *field;
+
+    if (!csv->tail) {
+        field = new_field(data, length, row, col);
+        csv->tail = field;
+        csv->head = field;
+    } else {
+        if (csv->tail->row == row && csv->tail->col == col) {
+            strncat(csv->tail->data, data, length);
+        } else {
+            field = new_field(data, length, row, col);
+            csv->tail->next = field;
+            csv->tail = field;
+        }
+    }
+
+    return 0;
+}
+
+
+int main(int argc, const char *argv[])
+{
+    csv_t csv;
+    field_t *field;
+    char buffer[64];
+    ssize_t nread;
+    csv_parser_t parser;
+    csv_parser_settings_t settings;
+
+    csv.head = NULL;
+    csv.tail = NULL;
+
+    settings.delimiter = ',';
+    settings.field_cb = field_cb;
+
+    csv_parser_init(&parser);
+    parser.data = &csv;
+
+    int fd = open("iris.csv", O_RDONLY);
+    if (fd == -1) {
+        perror("open");
+        return -1;
+    }
+
+    while ((nread = read(fd, buffer, sizeof(buffer))) > 0) {
+        csv_parser_execute(&parser, &settings, buffer, nread);
+    }
+
+    close(fd);
+
+    field = csv.head;
+    while (field) {
+        printf("row: %3d, col: %3d, data: %s\n", field->row, field->col, field->data);
+        field_t *next = field->next;
+        free(field);
+        field = next;
+    }
+
+    return 0;
+}