csv parser

12 files changed, 784 insertions, 0 deletions

diff --git a/.gitignore b/.gitignore
index 5caca14..53b72f2 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,4 +1,5 @@
 *.o
+src/libcsv_parser.a
 config
 config.log
 aclocal.m4
@@ -7,3 +8,5 @@ configure
 config.status
 Makefile.in
 Makefile
+.deps
+.dirstamp
diff --git a/Makefile.am b/Makefile.am
new file mode 100644
index 0000000..4dc0a2c
--- /dev/null
+++ b/Makefile.am
@@ -0,0 +1,9 @@
+ACLOCAL_AMFLAGS = -I config
+
+SUBDIRS = src
+
+DIST_SUBDIRS = src
+
+EXTRA_DIST = \
+	autogen.sh	\
+	LICENSE
diff --git a/autogen.sh b/autogen.sh
new file mode 100755
index 0000000..9e90913
--- /dev/null
+++ b/autogen.sh
@@ -0,0 +1,28 @@
+#!/bin/sh
+
+# Script to generate all required files from a git checkout
+
+command -v libtool > /dev/null 2>&1
+if [ $? -ne 0 ]; then
+    echo "autogen.sh: error: could not find libtool. libtool is required to run autogen.sh." 1>&2
+    exit 1
+fi
+
+command -v autoreconf > /dev/null 2>&1
+
+if [ $? -ne 0 ]; then
+    echo "autogen.sh: error: could not find autoreconf. autoconf and automake are required to run autogen.sh." 1>&2
+    exit 1
+fi
+
+mkdir -p ./config
+if [ $? -ne 0 ]; then
+   echo "autogen.sh: error: could not create directory: ./config." 1>&2
+   exit 1
+fi
+
+autoreconf --install --force --verbose -I config
+if [ $? -ne 0 ]; then
+   echo "autogen.sh: error: autoreconf exited with status $?" 1>&2
+   exit 1
+fi
diff --git a/configure.in b/configure.in
new file mode 100644
index 0000000..99ee5b7
--- /dev/null
+++ b/configure.in
@@ -0,0 +1,20 @@
+AC_PREREQ([2.69])
+AC_INIT([csv_parser], [0.1.0], [vilkeliskis.t@gmail.com])
+AC_CONFIG_AUX_DIR(config)
+AC_CONFIG_MACRO_DIR(config)
+AM_INIT_AUTOMAKE(tar-ustar dist-zip foreign subdir-objects)
+
+AC_PROG_RANLIB
+# This lets us use PACKAGE_VERSION in Makefiles
+AC_SUBST(PACKAGE_VERSION)
+
+# Take a copy of original flags
+CHIMP_ORIG_CFLAGS="${CFLAGS:-none}"
+CHIMP_ORIG_CPPFLAGS="${CPPFLAGS:-none}"
+CHIMP_ORIG_CXXFLAGS="${CXXFLAGS:-none}"
+
+# Checks for programs.
+AC_PROG_CC
+
+AC_CONFIG_FILES([Makefile src/Makefile tests/Makefile examples/Makefile])
+AC_OUTPUT
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;
+}
diff --git a/src/Makefile.am b/src/Makefile.am
new file mode 100644
index 0000000..417383e
--- /dev/null
+++ b/src/Makefile.am
@@ -0,0 +1,4 @@
+noinst_LIBRARIES = libcsv_parser.a
+
+libcsv_parser_a_SOURCES = csv_parser.c \
+                          csv_parser.h
diff --git a/src/csv_parser.c b/src/csv_parser.c
new file mode 100644
index 0000000..29f0529
--- /dev/null
+++ b/src/csv_parser.c
@@ -0,0 +1,152 @@
+/**
+ * Copyright (C) 2013 Tadas Vilkeliskis <vilkeliskis.t@gmail.com>
+ *
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy of
+ * this software and associated documentation files (the "Software"), to deal in
+ * the Software without restriction, including without limitation the rights to
+ * use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is furnished to do
+ * so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#include <assert.h>
+#include <stdlib.h>
+#include <csv_parser.h>
+
+
+void csv_parser_init(csv_parser_t *parser)
+{
+    assert(parser);
+    parser->state = csvps_line_start;
+    parser->row = -1;
+    parser->col = -1;
+    parser->nread = 0;
+    parser->data = NULL;
+}
+
+
+size_t csv_parser_execute(csv_parser_t *parser,
+                          const csv_parser_settings_t *settings,
+                          const char *data,
+                          size_t data_len)
+{
+    assert(parser);
+    assert(settings);
+    assert(data);
+
+    const char *cursor = data;
+    const char *field_value = NULL;
+    const char *data_end = data + data_len;
+    int r;
+    parser->nread = 0;
+
+    if (data_len < 1) {
+        return 0;
+    }
+
+    while (cursor < data_end) {
+        char ch = *cursor;
+        switch (parser->state) {
+            case csvps_line_start:
+                field_value = NULL;
+                parser->row += 1;
+                parser->col = -1;
+                if (ch == '\r' || ch == '\n') {
+                    parser->state = csvps_line_end_begin;
+                } else {
+                    parser->state = csvps_field_start;
+                }
+                break;
+            case csvps_field_start:
+                parser->col += 1;
+                parser->state = csvps_field_value;
+                field_value = cursor;
+                break;
+            case csvps_field_value:
+                if (ch == settings->delimiter) {
+                    parser->state = csvps_field_end;
+                } else if (ch == '\r' || ch == '\n') {
+                    parser->state = csvps_line_end_begin;
+                } else {
+                    // If we previously been in csvps_field_value state
+                    // and field_value is not set, set it right away.
+                    // This can happen when we execute parser multiple
+                    // times in the value state.
+                    if (field_value == NULL) {
+                        field_value = cursor;
+                    }
+
+                    cursor++;
+                    if (cursor == data_end) {
+                        if (settings->field_cb && field_value) {
+                            r = settings->field_cb(parser,
+                                                   field_value,
+                                                   cursor - field_value,
+                                                   parser->row,
+                                                   parser->col);
+                            if (r) {
+                                return parser->nread;
+                            }
+                        }
+                    }
+                    parser->nread++;
+                }
+                break;
+            case csvps_field_end:
+                // callback
+                if (settings->field_cb && field_value) {
+                    r = settings->field_cb(parser,
+                                           field_value,
+                                           cursor - field_value,
+                                           parser->row,
+                                           parser->col);
+                    if (r) {
+                        return parser->nread;
+                    }
+                }
+
+                parser->state = csvps_field_start;
+                cursor++;
+                parser->nread++;
+                break;
+            case csvps_line_end_begin:
+                // callback
+                if (settings->field_cb && field_value) {
+                    r = settings->field_cb(parser,
+                                           field_value,
+                                           cursor - field_value,
+                                           parser->row,
+                                           parser->col);
+                    if (r) {
+                        return parser->nread;
+                    }
+                }
+                parser->state = csvps_line_end;
+                break;
+            case csvps_line_end:
+                if (ch == '\r' || ch == '\n') {
+                    cursor++;
+                    parser->nread++;
+                } else {
+                    parser->state = csvps_line_start;
+                }
+                break;
+            default:
+                assert(0 && "invalid parser state");
+                break;
+        }
+    }
+
+    return parser->nread;
+}
diff --git a/src/csv_parser.h b/src/csv_parser.h
new file mode 100644
index 0000000..2e263a2
--- /dev/null
+++ b/src/csv_parser.h
@@ -0,0 +1,92 @@
+/**
+ * Copyright (C) 2013 Tadas Vilkeliskis <vilkeliskis.t@gmail.com>
+ *
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy of
+ * this software and associated documentation files (the "Software"), to deal in
+ * the Software without restriction, including without limitation the rights to
+ * use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ * of the Software, and to permit persons to whom the Software is furnished to do
+ * so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef CSV_PARSER_INCLUDE_GUARD_E95A7C4D_BE4A_49D1_8607_900F36DD25B8
+#define CSV_PARSER_INCLUDE_GUARD_E95A7C4D_BE4A_49D1_8607_900F36DD25B8
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <stdint.h>
+#include <sys/types.h>
+
+
+typedef enum csv_parser_state_t {
+    csvps_line_start = 0,
+    csvps_field_start,
+    csvps_field_value,
+    csvps_field_end,
+    csvps_line_end_begin,
+    csvps_line_end
+} csv_parser_state_t;
+
+
+typedef struct csv_parser_t {
+    csv_parser_state_t state;
+    /* csv row */
+    int row;
+    /* csv column */
+    int col;
+    uint32_t nread;
+    /* user data */
+    void *data;
+} csv_parser_t;
+
+
+/**
+ * Field callback interface.
+ *
+ * Field callback can be called multiple times for the same row and column.
+ * It's up to the user to construct full field value.
+ *
+ * Return 0 value on success, anything else on error.
+ */
+typedef int (*csv_parser_field_calback_t)(csv_parser_t *parser,
+                                          const char *data,
+                                          size_t length,
+                                          int row,
+                                          int col);
+
+
+typedef struct csv_parser_settings_t {
+    char delimiter;
+    csv_parser_field_calback_t field_cb;
+} csv_parser_settings_t;
+
+
+void csv_parser_init(csv_parser_t *parser);
+
+/**
+ * Executes CSV parser on the given data. Returns number
+ * of bytes read.
+ */
+size_t csv_parser_execute(csv_parser_t *parser,
+                          const csv_parser_settings_t *settings,
+                          const char *data,
+                          size_t data_len);
+
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* end of include guard */
diff --git a/tests/Makefile.am b/tests/Makefile.am
new file mode 100644
index 0000000..2b70ec5
--- /dev/null
+++ b/tests/Makefile.am
@@ -0,0 +1,8 @@
+AM_CPPFLAGS = -I$(top_srcdir)/src
+
+bin_PROGRAMS = test
+
+test_LDFLAGS = -lcheck
+test_SOURCES = ../src/csv_parser.c \
+               ../src/csv_parser.h \
+               main.c
diff --git a/tests/main.c b/tests/main.c
new file mode 100644
index 0000000..685842f
--- /dev/null
+++ b/tests/main.c
@@ -0,0 +1,215 @@
+#include <check.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <csv_parser.h>
+
+
+struct test_results {
+    int test_case_number;
+    int *results;
+};
+
+
+// 5 items per row, 3 rows per test case: 15 * 6 slots
+static int expected_test_results[] = {
+    // ""
+    -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+    // ", "
+    0, 1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+    // ","
+    0, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+    // "\n"
+    -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+    // "\r\n",
+    -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+    // "a,b,,c,"
+    1, 2, 0, 1, -1,
+    -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+    // "a,b,,c, "
+    1, 2, 0, 1, 1,
+    -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+    // "a,b,\na,b,"
+    1, 2, 0, -1, -1,
+    1, 1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+    // " bc "
+    4, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1,
+};
+
+
+static const int results_size = sizeof(expected_test_results);
+static const int result_slots = sizeof(expected_test_results)/sizeof(int);
+
+
+static const char *test_data[] = {
+    "",
+    ", ",
+    ",",
+    "\n",
+    "\r\n",
+    "a,bb,,c,",
+    "a,bb,,c, ",
+    "a,bb,\na,b,",
+    " bc ",
+};
+
+
+static int test_data_end_states[] = {
+    csvps_line_start,
+    csvps_field_value,
+    csvps_field_start,
+    csvps_line_end,
+    csvps_line_end,
+    csvps_field_start,
+    csvps_field_value,
+    csvps_field_start,
+    csvps_field_value,
+};
+
+static int num_test_cases = sizeof(test_data)/(sizeof(char*));
+
+
+void init_test_results(int *data, int len)
+{
+    int i;
+    for (i = 0; i < len; i++) {
+        data[i] = -1;
+    }
+}
+
+
+void print_results(int *data, int len)
+{
+    int i;
+    for (i = 0; i < len; i++) {
+        if (i != 0 && i % 5 == 0) {
+            printf("\n");
+        }
+        printf("%4d ", data[i]);
+    }
+
+    printf("\n");
+}
+
+
+int field_cb(csv_parser_t *parser, const char *data, size_t length, int row, int col)
+{
+    struct test_results *results = parser->data;
+    int slot = results->test_case_number * 15 + row * 5 + col;
+
+    if (results->results[slot] == -1) {
+        results->results[slot] = length;
+    } else {
+        results->results[slot] += length;
+    }
+    return 0;
+}
+
+
+START_TEST(test_parser_full)
+{
+    csv_parser_t parser;
+    csv_parser_settings_t settings;
+    struct test_results results;
+    int i;
+
+    settings.delimiter = ',';
+    settings.field_cb = field_cb;
+
+    results.results = malloc(results_size);
+    init_test_results(results.results, result_slots);
+    for (i = 0; i < num_test_cases; i++) {
+        const char *str = test_data[i];
+        int len = strlen(str);
+
+        results.test_case_number = i;
+
+        csv_parser_init(&parser);
+        parser.data = &results;
+
+        int nread = csv_parser_execute(&parser, &settings, str, len);
+        ck_assert_int_eq(len, nread);
+        ck_assert_int_eq(parser.state, test_data_end_states[i]);
+    }
+
+    printf("Test results:\n");
+    print_results(results.results, result_slots);
+    ck_assert_int_eq(0, memcmp(results.results, expected_test_results, results_size));
+    free(results.results);
+
+}
+END_TEST
+
+
+START_TEST(test_parser_chunked)
+{
+    csv_parser_t parser;
+    csv_parser_settings_t settings;
+    struct test_results results;
+    int i, offset;
+
+    settings.delimiter = ',';
+    settings.field_cb = field_cb;
+
+    results.results = malloc(results_size);
+    init_test_results(results.results, result_slots);
+    for (i = 0; i < num_test_cases; i++) {
+        const char *str = test_data[i];
+        int len = strlen(str);
+
+        results.test_case_number = i;
+
+        csv_parser_init(&parser);
+        parser.data = &results;
+
+        // parse string one char at a time
+        for (offset = 0; offset < len; offset++) {
+            char c = *(str+offset);
+            int nread = csv_parser_execute(&parser, &settings, &c, 1);
+            ck_assert_int_eq(1, nread);
+        }
+        ck_assert_int_eq(parser.state, test_data_end_states[i]);
+    }
+
+    printf("Test results:\n");
+    print_results(results.results, result_slots);
+    ck_assert_int_eq(0, memcmp(results.results, expected_test_results, results_size));
+    free(results.results);
+
+}
+END_TEST
+
+
+int main(int argc, const char *argv[])
+{
+    Suite *s = suite_create("csv_parser");
+    TCase *tc = tcase_create("parser");
+    tcase_add_test(tc, test_parser_full);
+    tcase_add_test(tc, test_parser_chunked);
+
+    suite_add_tcase(s, tc);
+    SRunner *sr = srunner_create(s);
+
+    printf("Expected results:\n");
+    print_results(expected_test_results, result_slots);
+
+    srunner_run_all(sr, CK_VERBOSE);
+    srunner_free(sr);
+
+    return 0;
+}