1 整体概括：
前提说明:
本篇wget分析仅仅是参数解析内容，不包括wget的递归和非递归下载，后面文章会陆续进行分析。本次主要分析参数为tries(t) timeout(T) no-clobber quiet(q) recursive(r) help(h)version(V) append-output(a) execute(e) no(n) clobber, 其中括号里面的为wget短选项，括号前面的为长选项。
在wget运行下载文件或页面时，用户可以通过参数来改变wget的行为，比如想查看wget的调试和http数据包可以使用 wget –debug
www.baidu.com/index.html
。
我们这次分析下载url以baidu 搜索页面(
http://www.baidu.com/index.html
)为样本，进行分析不同类型的参数，以达到抛砖引玉的目的。wget支持长选项和短选项，比如输出调试信息短选项为-d长选项为—debug
wget有全局的struct options opt；保存着wget用户参数设置值，来修改wget行为。本篇主要讲解用户输入参数如何转化为 opt的成员。
wget分析的版本为1.13，gcc版本为3.4.5，linux内核版本2.6.9_5-9-0-0
2 详细代码解析:
2.1数据结构
wget 对于配置转化，设置struct options opt 有两张表和长短选项数组
命令行表:
struct cmdline_option option_data
此表保存着wget支持的长短选项和长短选项属性
命令转化设置opt表:
commands
此表用于设置根据参数来设置opt成员。
长选项:
struct option long_options[2*countof(option_data) + 1]
短选项:
struct char short_options[128]
2.2参数解析流程
Main 首先根据不同平台来设置使用时间函数，blog里有monotonic time和wall time讲解，这里就不分析。
2.2.1 defaults();
然后调用defaults函数，该函数主要是给全局opt设置默认值(
因为代码太长，给出部分代码
)。
//#######################src/init.c
/* Reset the variables to default values. */
void
defaults (void)
{
char *tmp;
/* Most of the default values are 0 (and 0.0, NULL, and false).
Just reset everything, and fill in the non-zero values. Note
that initializing pointers to NULL this way is technically
illegal, but porting Wget to a machine where NULL is not all-zero
bit pattern will be the least of the implementors' worries. */
xzero (opt);
opt.cookies = true;
opt.verbose = -1;
opt.ntry = 20;
opt.reclevel = 5;
opt.add_hostdir = true;
opt.netrc = true;
opt.ftp_glob = true;
2.2.2 init_switches()
函数很简单，追加一些ch注释
static void
init_switches (void)
{
//p指向短选项数组
char *p = short_options;
size_t i, o = 0;
//遍历所有选项
for (i = 0; i < countof (option_data); i++)
{
struct cmdline_option *opt = &option_data[i];
struct option *longopt;
//如果这个选项数据没有长选项，直接跳过
if (!opt->long_name)
/* The option is disabled. */
continue;
//longopt指向长选项一个依次节点
longopt = &long_options[o++];
//长选项name指向opt的long_name
longopt->name = opt->long_name;
//长选项val执行opt的数组索引，用于根据长选项查找opt
longopt->val = i;
if (opt->short_name)
{
//如果存在短选项，把opt short_name保存在short_options中
*p++ = opt->short_name;
//用optmap保存short_name的value 来索引长选项数组
optmap[opt->short_name - 32] = longopt - long_options;
}
switch (opt->type)
{
case OPT_VALUE:
//参数需要值
longopt->has_arg = required_argument;
//如果参数需要设置值，并且短选项存在，就需要字符":"
if (opt->short_name)
*p++ = ':';
break;
case OPT_BOOLEAN:
/* 如果是bool类型(开关类型参数) 需要支持--option=off and --no-option .look the note of the blow*/
/* Specify an optional argument for long options, so that
--option=off works the same as --no-option, for
compatibility with pre-1.10 Wget. However, don't specify
optional arguments short-option booleans because they
prevent combining of short options. */
longopt->has_arg = optional_argument;
/* For Boolean options, add the "--no-FOO" variant, which is
identical to "--foo", except it has opposite meaning and
it doesn't allow an argument. */
longopt = &long_options[o++];
longopt->name = no_prefix (opt->long_name);
longopt->has_arg = no_argument;
/* Mask the value so we'll be able to recognize that we're
dealing with the false value. */
//索引加一个负数符号
longopt->val = i | BOOLEAN_NEG_MARKER;
break;
default:
//others 根据情况设置不同的值
assert (opt->argtype != -1);
longopt->has_arg = opt->argtype;
if (opt->short_name)
{
if (longopt->has_arg == required_argument)
*p++ = ':';
/* Don't handle optional_argument */
}
}
}
/* Terminate short_options. */
*p = '\0';
/* No need for xzero(long_options[o]) because its storage is static
and it will be zeroed by default. */
assert (o <= countof (long_options));
}
举例分析(长选项为append-output ，短(a)):
用gdb跟踪下long_options和short_options
截取long_options一部分:
name(append-output) has_arg(1) val(2)
val==2 表示该长选项属性在option_data的索引
其中字符’a’ ascii值为97 那么这个在opt_map中索引为97-32=65
Such
也就可以通过短选项找个长选项索引，然后这个长选项val就是option_data的数组索引。
2.2.1 main set opt
while ((ret = getopt_long (argc, argv,
short_options, long_options, &longindex)) != -1)
{
int val;
struct cmdline_option *opt;
/* If LONGINDEX is unchanged, it means RET is referring a short
option. */
if (longindex == -1)
{
if (ret == '?')
{
print_usage (0);
printf ("\n");
printf (_("Try `%s --help' for more options.\n"), exec_name);
exit (2);
}
/* Find the short option character in the mapping. */
longindex = optmap[ret - 32];
}
val = long_options[longindex].val;
/* Use the retrieved value to locate the option in the
option_data array, and to see if we're dealing with the
negated "--no-FOO" variant of the boolean option "--foo". */
opt = &option_data[val & ~BOOLEAN_NEG_MARKER];
我截取了main处理argc argv部分代码。
调用过api getopt_long, 如果longindex==-1那么用户输入的是短选项，通过optmap来确定此短选项在长选项数组索引optmap[ret-32], 然后根据长选项的val找到在opt_data的此选项位置,如果用户输入的是长选项，就直接使用val。
val = long_options[longindex].val;
获取此选项opt_data
opt = &option_data[val &~BOOLEAN_NEG_MARKER];
找到了参数在opt_data的位置，然后下面就开始设置全局opt
根据参数类型分析以下参数:
OPT_VALUE tries(t) timeout(T)
OPT_BOOLEAN no-clobber quiet(q) recursive(r)
OPT_FUNCALL help(h) version(V)
OPT__APPEND_OUTPUT append-output(a)
OPT_EXECUTE execute(e)
OPT_NO no(n)
OPT__PARENT|OPT__CLOBBER clobber
代码段：
switch (opt->type)
{
case OPT_VALUE:
setoptval (opt->data, optarg, opt->long_name);
break;
case OPT_BOOLEAN:
if (optarg)
/* The user has specified a value -- use it. */
setoptval (opt->data, optarg, opt->long_name);
else
{
/* NEG is true for `--no-FOO' style boolean options. */
bool neg = !!(val & BOOLEAN_NEG_MARKER);
setoptval (opt->data, neg ? "0" : "1", opt->long_name);
}
break;
case OPT_FUNCALL:
{
void (*func) (void) = (void (*) (void)) opt->data;
func ();
}
break;
case OPT__APPEND_OUTPUT:
setoptval ("logfile", optarg, opt->long_name);
append_to_log = true;
break;
case OPT__EXECUTE:
run_command (optarg);
break;
case OPT__NO:
{
/* We support real --no-FOO flags now, but keep these
short options for convenience and backward
compatibility. */
char *p;
for (p = optarg; p && *p; p++)
switch (*p)
{
case 'v':
setoptval ("verbose", "0", opt->long_name);
break;
case 'H':
setoptval ("addhostdir", "0", opt->long_name);
break;
case 'd':
setoptval ("dirstruct", "0", opt->long_name);
break;
case 'c':
setoptval ("noclobber", "1", opt->long_name);
break;
case 'p':
setoptval ("noparent", "1", opt->long_name);
break;
default:
fprintf (stderr, _("%s: illegal option -- `-n%c'\n"),
exec_name, *p);
print_usage (1);
fprintf (stderr, "\n");
fprintf (stderr, _("Try `%s --help' for more options.\n"),
exec_name);
exit (1);
}
break;
}
case OPT__PARENT:
case OPT__CLOBBER:
case OPT__CLOBBER:
{
/* The wgetrc commands are named noparent and noclobber,
so we must revert the meaning of the cmdline options
before passing the value to setoptval. */
bool flag = true;
if (optarg)
flag = (*optarg == '1' || c_tolower (*optarg) == 'y'
|| (c_tolower (optarg[0]) == 'o'
&& c_tolower (optarg[1]) == 'n'));
setoptval (opt->type == OPT__PARENT ? "noparent" : "noclobber",
flag ? "0" : "1", opt->long_name);
break;
}
case OPT__DONT_REMOVE_LISTING:
setoptval ("removelisting", "0", opt->long_name);
break;
}
longindex = -1;
}
参数类型OPT_VALUE(t,T)
Setoptval(opt->data, optarg,opt->long_name)
->setval_internal(command_by_name(opt->data),“–“+opt->long_name, optarg)
其中command_by_name(opt->data)是通过二分查找，找到data在commands中的索引位置
Code:
static int
command_by_name (const char *cmdname)
{
/* Use binary search for speed. Wget has ~100 commands, which
guarantees a worst case performance of 7 string comparisons. */
int lo = 0, hi = countof (commands) - 1;
while (lo <= hi)
{
int mid = (lo + hi) >> 1;
int cmp = strcasecmp (cmdname, commands[mid].name);
if (cmp < 0)
hi = mid - 1;
else if (cmp > 0)
lo = mid + 1;
else
return mid;
}
return -1;
}
set_internal(comind, “–“+opt->long_name,optarg)
->commands[comind].action (“–“+opt->long_name, optarg,commands[comind].place);
比如tries commands信息如下
{ “tries”, &opt.ntry, cmd_number_inf },
调用cmd_num_inf(“—tries”, optarg, opt.ntry)
函数设置opt.ntry = strtoul(optarg, 10,. NULL)
参数类型OPT_BOOLEAN
和OPT_BOOLEAN大同小异，此处略过。
参数类型OPT_FUNCALL
-h 和 –v
调用opt->data
如果用户输入参数为-h或者-v就会调用print_help or print_version，这里就略过了。
参数类型OPT__APPEND_OUTPUT
setoptval (“logfile”, optarg,opt->long_name);//和OPT_VALUE相似，略过。
参数类型OPT__EXECUTE
参数-e
Run_command(optarg)
其中optarg 格式为key=value，此函数解析出key和value，比如append-output=logfile.txt
就会调用set_internal(comind, com, val)来设置opt
参数类型OPT__NO、OPT__PARENT、OPT__CLOBBER、OPT__DONT_REMOVE_LISTING都是大同小异，这里就略过了。
此篇文章就结束了。
2014/4/12 Leek in beijing