From d3a60bac6c6aae62ced6eec21b3865caaab83bb8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ludovic=20Court=C3=A8s?= Date: Thu, 11 Jan 2018 15:29:55 +0100 Subject: [PATCH] 'get-bytevector-some' reads as much as possible without blocking. Fixes . * libguile/ports.c (scm_i_read_bytes): Remove 'static' keyword. * libguile/ports.h (SCM_UNBUFFEREDP): New macro. (scm_i_read_bytes): New declaration. * libguile/r6rs-ports.c (scm_get_bytevector_some): When PORT is unbuffered, invoke 'scm_i_read_bytes' to read as much as we can. * test-suite/tests/r6rs-ports.test ("8.2.8 Binary Input") ["get-bytevector-some [unbuffered port]"] ["get-bytevector-some [unbuffered port, lookahead-u8]"] ["get-bytevector-some [unbuffered port, unget-bytevector]"]: New tests. --- libguile/ports.c | 6 ++++-- libguile/ports.h | 7 ++++++- libguile/r6rs-ports.c | 34 ++++++++++++++++++++++++++++------ test-suite/tests/r6rs-ports.test | 36 ++++++++++++++++++++++++++++++++++-- 4 files changed, 72 insertions(+), 11 deletions(-) diff --git a/libguile/ports.c b/libguile/ports.c index 72bb73a01..002dd1433 100644 --- a/libguile/ports.c +++ b/libguile/ports.c @@ -1,4 +1,4 @@ -/* Copyright (C) 1995-2001, 2003-2004, 2006-2017 +/* Copyright (C) 1995-2001, 2003-2004, 2006-2018 * Free Software Foundation, Inc. * * This library is free software; you can redistribute it and/or @@ -1543,7 +1543,9 @@ scm_peek_byte_or_eof (SCM port) return peek_byte_or_eof (port, &buf, &cur); } -static size_t +/* Like read(2), read *up to* COUNT bytes from PORT into DST, starting + at OFFSET. Return 0 upon EOF. */ +size_t scm_i_read_bytes (SCM port, SCM dst, size_t start, size_t count) { size_t filled; diff --git a/libguile/ports.h b/libguile/ports.h index d131db5be..3fe64c27d 100644 --- a/libguile/ports.h +++ b/libguile/ports.h @@ -4,7 +4,7 @@ #define SCM_PORTS_H /* Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2003, 2004, - * 2006, 2008, 2009, 2010, 2011, 2012, 2013, 2014 Free Software Foundation, Inc. + * 2006, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2018 Free Software Foundation, Inc. * * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public License @@ -71,7 +71,10 @@ SCM_INTERNAL SCM scm_i_port_weak_set; #define SCM_CLOSEDP(x) (!SCM_OPENP (x)) #define SCM_CLR_PORT_OPEN_FLAG(p) \ SCM_SET_CELL_WORD_0 ((p), SCM_CELL_WORD_0 (p) & ~SCM_OPN) + #ifdef BUILDING_LIBGUILE +#define SCM_UNBUFFEREDP(x) \ + (SCM_PORTP (x) && (SCM_CELL_WORD_0 (x) & SCM_BUF0)) #define SCM_PORT_FINALIZING_P(x) \ (SCM_CELL_WORD_0 (x) & SCM_F_PORT_FINALIZING) #define SCM_SET_PORT_FINALIZING(p) \ @@ -185,6 +188,8 @@ SCM_API int scm_get_byte_or_eof (SCM port); SCM_API int scm_peek_byte_or_eof (SCM port); SCM_API size_t scm_c_read (SCM port, void *buffer, size_t size); SCM_API size_t scm_c_read_bytes (SCM port, SCM dst, size_t start, size_t count); +SCM_INTERNAL size_t scm_i_read_bytes (SCM port, SCM dst, size_t start, + size_t count); SCM_API scm_t_wchar scm_getc (SCM port); SCM_API SCM scm_read_char (SCM port); diff --git a/libguile/r6rs-ports.c b/libguile/r6rs-ports.c index e944c7aab..a3d638ca0 100644 --- a/libguile/r6rs-ports.c +++ b/libguile/r6rs-ports.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009, 2010, 2011, 2013-2015 Free Software Foundation, Inc. +/* Copyright (C) 2009, 2010, 2011, 2013-2015, 2018 Free Software Foundation, Inc. * * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public License @@ -481,9 +481,9 @@ SCM_DEFINE (scm_get_bytevector_some, "get-bytevector-some", 1, 0, 0, "position to point just past these bytes.") #define FUNC_NAME s_scm_get_bytevector_some { - SCM buf; + SCM buf, bv; size_t cur, avail; - SCM bv; + const size_t max_buffer_size = 4096; SCM_VALIDATE_BINARY_INPUT_PORT (1, port); @@ -494,9 +494,31 @@ SCM_DEFINE (scm_get_bytevector_some, "get-bytevector-some", 1, 0, 0, return SCM_EOF_VAL; } - bv = scm_c_make_bytevector (avail); - scm_port_buffer_take (buf, (scm_t_uint8 *) SCM_BYTEVECTOR_CONTENTS (bv), - avail, cur, avail); + if (SCM_UNBUFFEREDP (port) && (avail < max_buffer_size)) + { + /* PORT is unbuffered. Read as much as possible from PORT. */ + size_t read; + + bv = scm_c_make_bytevector (max_buffer_size); + scm_port_buffer_take (buf, (scm_t_uint8 *) SCM_BYTEVECTOR_CONTENTS (bv), + avail, cur, avail); + + read = scm_i_read_bytes (port, bv, avail, + SCM_BYTEVECTOR_LENGTH (bv) - avail); + + if (read == 0) + scm_port_buffer_set_has_eof_p (buf, SCM_BOOL_F); + + if (read + avail < SCM_BYTEVECTOR_LENGTH (bv)) + bv = scm_c_shrink_bytevector (bv, read + avail); + } + else + { + /* Return what's already buffered. */ + bv = scm_c_make_bytevector (avail); + scm_port_buffer_take (buf, (scm_t_uint8 *) SCM_BYTEVECTOR_CONTENTS (bv), + avail, cur, avail); + } return bv; } diff --git a/test-suite/tests/r6rs-ports.test b/test-suite/tests/r6rs-ports.test index ba3131f2e..d5476f20e 100644 --- a/test-suite/tests/r6rs-ports.test +++ b/test-suite/tests/r6rs-ports.test @@ -1,6 +1,6 @@ ;;;; r6rs-ports.test --- R6RS I/O port tests. -*- coding: utf-8; -*- ;;;; -;;;; Copyright (C) 2009-2012, 2013-2015 Free Software Foundation, Inc. +;;;; Copyright (C) 2009-2012, 2013-2015, 2018 Free Software Foundation, Inc. ;;;; Ludovic Courtès ;;;; ;;;; This library is free software; you can redistribute it and/or @@ -26,7 +26,8 @@ #:use-module (rnrs io ports) #:use-module (rnrs io simple) #:use-module (rnrs exceptions) - #:use-module (rnrs bytevectors)) + #:use-module (rnrs bytevectors) + #:use-module ((ice-9 binary-ports) #:select (unget-bytevector))) (define-syntax pass-if-condition (syntax-rules () @@ -183,6 +184,37 @@ (equal? (bytevector->u8-list bv) (map char->integer (string->list str)))))) + (pass-if-equal "get-bytevector-some [unbuffered port]" + (string->utf8 "Hello, world!") + ;; 'get-bytevector-some' used to return a single byte, see + ;; . + (call-with-input-string "Hello, world!" + (lambda (port) + (setvbuf port _IONBF) + (get-bytevector-some port)))) + + (pass-if-equal "get-bytevector-some [unbuffered port, lookahead-u8]" + (string->utf8 "Hello, world!") + (call-with-input-string "Hello, world!" + (lambda (port) + (setvbuf port _IONBF) + + ;; 'lookahead-u8' fills in PORT's 1-byte buffer. Yet, + ;; 'get-bytevector-some' should return the whole thing. + (and (eqv? (lookahead-u8 port) (char->integer #\H)) + (get-bytevector-some port))))) + + (pass-if-equal "get-bytevector-some [unbuffered port, unget-bytevector]" + (string->utf8 "Hello") + (call-with-input-string "Hello, world!" + (lambda (port) + (setvbuf port _IONBF) + ;; 'unget-bytevector' fills the putback buffer, and + ;; 'get-bytevector-some' should get data from there. + (unget-bytevector port (get-bytevector-all port) + 0 5) + (get-bytevector-some port)))) + (pass-if "get-bytevector-all" (let* ((str "GNU Guile") (index 0) -- 2.15.1