log_reader.c File Reference

The CSV reader's byte layer: the sources behind the read/rewind function pointers, the row splitter that handles quoting and line endings, and the delimiter sniffer. More...

#include <ctype.h>
#include <limits.h>
#include <stdio.h>
#include <string.h>
#include "log_csv.h"
#include "log_csv_int.h"

Macros
#define	SNIFF_LINES   25
	Most non-blank lines the delimiter sniffer looks at.

Functions
static size_t	mem_read (void *ctx, char *buf, size_t max)
	Read from a memory source.
static bool	mem_rewind (void *ctx)
	Rewind a memory source to its start.
static bool	mem_size (void *ctx, size_t *bytes)
	Length of a memory source.
static bool	mem_seek (void *ctx, size_t offset)
	Move a memory source's read position.
void	log_source_memory (log_source_t *src, log_mem_ctx_t *ctx, const char *text, size_t len)
	A source over a block of memory.
static size_t	file_read (void *ctx, char *buf, size_t max)
	Read from a stdio file.
static bool	file_error (void *ctx)
	Whether the last read of a stdio file failed.
static bool	file_rewind (void *ctx)
	Rewind a stdio file to its start.
static bool	file_size (void *ctx, size_t *bytes)
	fseek and ftell take a long: 2GiB less 1 byte on the panel.
static bool	file_seek (void *ctx, size_t offset)
	Move a stdio file's read position.
void	log_source_stdio (log_source_t *src, void *file)
	A source over an open stdio stream. file is a FILE*.
void	log_reader_init (log_reader_t *r, log_source_t *src)
	Set up a row splitter.
static int	reader_fill (log_reader_t *r)
	Refill the read-ahead buffer when it is empty.
static int	reader_getc (log_reader_t *r)
	Read one byte, skipping a leading byte order mark.
static int	reader_peek (log_reader_t *r)
	Look at the next byte without taking it.
int	log_reader_row (log_reader_t *r, char delimiter, char *store, size_t store_size, char **fields, int max_fields, int *total_fields)
	Read one row.
const char *	log_csv_delimiter_label (char delimiter)
	Label of a delimiter.
static int	count_fields (const char *s, size_t len, char delimiter)
	Count the fields a delimiter makes in one line.
char	log_csv_sniff (const char *sample, size_t len)
	Guess the delimiter from a text sample: the most consistent, widest split.

Variables
static char	s_empty [1] = ""
	Empty field text, for fields that did not fit the store.
const char	log_csv_delimiters [4] = { ';', ',', '\t', '|' }
	The candidate delimiters, in the order they are scored.

Detailed Description

The CSV reader's byte layer: the sources behind the read/rewind function pointers, the row splitter that handles quoting and line endings, and the delimiter sniffer.

A source is a string in memory (tests, the sniff sample) or a stdio file (the card); the row splitter reads either through log_source_t and never holds more than one buffer of it. The splitter and the sniffer take no allocation; the allocator and the analysis built on them are in log_csv.c.

SPDX-License-Identifier: MIT

Function Documentation

count_fields()

int count_fields ( const char * s, size_t len, char delimiter )

static

Count the fields a delimiter makes in one line.

Delimiters inside a quoted field are not counted.

Parameters

s	The line.
len	Length of the line, bytes.
delimiter	The candidate delimiter.

Returns

The number of fields, at least 1.

file_error()

bool file_error ( void * ctx )

static

Whether the last read of a stdio file failed.

Parameters

ctx	The FILE *.

Returns

true when the stream has its error flag set.

file_read()

size_t file_read ( void * ctx, char * buf, size_t max )

static

Read from a stdio file.

Parameters

ctx	The FILE *.
buf	Receives the bytes.
max	Capacity of buf, bytes.

Returns

Bytes read; 0 at the end of the file or on an error.

file_rewind()

bool file_rewind ( void * ctx )

static

Rewind a stdio file to its start.

Parameters

ctx	The FILE *.

Returns

true when the seek succeeded.

file_seek()

bool file_seek ( void * ctx, size_t offset )

static

Move a stdio file's read position.

Parameters

ctx	The FILE *.
offset	New position, bytes from the start.

Returns

true when the seek succeeded; false when offset exceeds LONG_MAX.

file_size()

bool file_size ( void * ctx, size_t * bytes )

static

fseek and ftell take a long: 2GiB less 1 byte on the panel.

A file longer than that answers false, and the analysis reads it on instead.

Parameters

ctx	The FILE *.
bytes	Receives the length, bytes.

Returns

true when the length was read.

log_csv_delimiter_label()

const char * log_csv_delimiter_label

(

char

delimiter

)

Label of a delimiter.

Parameters

delimiter

The delimiter.

Returns

A static text.

log_csv_sniff()

char log_csv_sniff	(	const char *	sample,
		size_t	len )

Guess the delimiter from a text sample: the most consistent, widest split.

Parameters

sample	The sample text.
len	Length of sample, bytes.

Returns

The delimiter.

log_reader_init()

void log_reader_init	(	log_reader_t *	r,
		log_source_t *	src )

Set up a row splitter.

Parameters

r	The splitter.
src	The input.

log_reader_row()

int log_reader_row	(	log_reader_t *	r,
		char	delimiter,
		char *	store,
		size_t	store_size,
		char **	fields,
		int	max_fields,
		int *	total_fields )

Read one row.

A row ends at its line feed (0x0A). Input that ends inside a row – a write cut off by a power loss or a full card – leaves a row nothing proves complete: a number cut after two of its four digits still parses, and the field count can still match the header. That row is not returned: the call answers -1 as at the end of input and sets r->cut.

Parameters

r	The splitter.
delimiter	The field delimiter.
store	scratch for the field text; fields point into it
store_size	Size of store, bytes.
fields	receives one pointer per field, up to max_fields
max_fields	Capacity of fields, in pointers.
total_fields	receives the true field count, which may exceed max_fields; that is how a ragged row is spotted

Returns

the number of fields stored, or -1 at end of input

log_source_memory()

void log_source_memory	(	log_source_t *	src,
		log_mem_ctx_t *	ctx,
		const char *	text,
		size_t	len )

A source over a block of memory.

Parameters

src	Receives the source.
ctx	Holds the read position; set to the start of text.
text	The bytes read.
len	Length of text, bytes.

log_source_stdio()

void log_source_stdio	(	log_source_t *	src,
		void *	file )

A source over an open stdio stream. file is a FILE*.

Parameters

src	Receives the source.
file	An open stream, a FILE *.

mem_read()

size_t mem_read ( void * ctx, char * buf, size_t max )

static

Read from a memory source.

Parameters

ctx	The log_mem_ctx_t.
buf	Receives the bytes.
max	Capacity of buf, bytes.

Returns

Bytes copied; 0 at the end of the text.

mem_rewind()

bool mem_rewind ( void * ctx )

static

Rewind a memory source to its start.

Parameters

ctx	The log_mem_ctx_t.

Returns

true, always.

mem_seek()

bool mem_seek ( void * ctx, size_t offset )

static

Move a memory source's read position.

Parameters

ctx	The log_mem_ctx_t.
offset	New position, bytes from the start.

Returns

false when offset is past the end.

mem_size()

bool mem_size ( void * ctx, size_t * bytes )

static

Length of a memory source.

Parameters

ctx	The log_mem_ctx_t.
bytes	Receives the length, bytes.

Returns

true, always.

reader_fill()

int reader_fill ( log_reader_t * r )

static

Refill the read-ahead buffer when it is empty.

Sets failed when the source reports an error at its end.

Parameters

r	The row splitter.

Returns

1 when bytes are buffered, 0 at the end of input.

reader_getc()

int reader_getc ( log_reader_t * r )

static

Read one byte, skipping a leading byte order mark.

Parameters

r	The row splitter.

Returns

The byte, 0 to 255, or -1 at the end of input.

reader_peek()

int reader_peek ( log_reader_t * r )

static

Look at the next byte without taking it.

Parameters

r	The row splitter.

Returns

The byte, 0 to 255, or -1 at the end of input.