finally release cat knowledgepage

homepage/index.html

@@ -71,6 +71,7 @@ I'm vaccinated against COVID-19. Are you?
 <A HREF="#privacy">#privacy</A>,
 <A HREF="/thegame">/thegame</A>;
 <B>knowledge</B>:
+<A HREF="/knowledge/cat/">cat(1)</A>;
 <A HREF="/knowledge/netbsd/">NetBSD</A>;
 <A HREF="/knowledge/true">true(1)</A>;
 <B>shilling</B>:

homepage/knowledge/cat/cat.c

@@ -0,0 +1,106 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#define STDIN_NAME "<stdin>"
+#define STDOUT_NAME "<stdout>"
+
+/* these are the predicted errors that could occur */
+enum error_type{
+	FILE_ACCESS,
+	FILE_CLOSE,
+	FILE_WRITE
+};
+
+/* this is an error function that will print to standard error the error that
+ * occurred in the program and exit */
+void
+error(enum error_type type, char *argv0, char *file_name){
+	switch(type){
+	case FILE_ACCESS:
+		fprintf(stderr, "%s: %s: cannot open file\n", argv0, file_name);
+		break;
+	case FILE_CLOSE:
+		fprintf(stderr, "%s: %s: cannot close file\n", argv0, file_name);
+		break;
+	case FILE_WRITE:
+		fprintf(stderr, "%s: %s: cannot write to file\n", argv0, file_name);
+		break;
+	}
+	exit(1);
+}
+
+/* print input to output, returns 0 if successful and 1 if unsuccessful */
+int
+file_copy(FILE *input, FILE *output){
+	char c;
+	while((c = getc(input)) != EOF)
+		if(putc(c, output) == EOF)
+			return 1;
+	return 0;
+}
+
+int
+main(int argc, char *argv[]){
+	/* the name of the file being printed (for diagnostics) */
+	char *file_name;
+
+	/* allocate this ahead of time */
+	char *stdin_file_name = STDIN_NAME;
+
+	/* the file pointer of the file being printed */
+	FILE *input;
+
+	/* this will always be stdout */
+	FILE *output = stdout;
+
+	int i;
+
+	/* whether or not options are being parsed */
+	int parsing_opts = 1;
+
+	/* usage with 0 arguments - print standard input to standard output */
+	if(argc == 1 && file_copy(stdin, stdout))
+		error(FILE_WRITE, argv[0], STDOUT_NAME);
+	else if(argc == 1)
+		return 0;
+
+	for(i = 1; i < argc; ++i){
+		/* parsing options */
+
+		/* after `--`, interpret `--`, `-`, and `-u` as literal
+		 * filenames */
+		if(parsing_opts && !strcmp(argv[i], "--")){
+			parsing_opts = 0;
+			continue;
+
+		/* ignore `-u` if still parsing options */
+		}else if(parsing_opts && !strcmp(argv[i], "-u"))
+			continue;
+
+		/* take `-` to mean standard input if still parsing options */
+		else if(parsing_opts && !strcmp(argv[i], "-")){
+			file_name = stdin_file_name;
+			input = stdin;
+
+		/* non-option; open the file and make sure file_name points to
+		 * the right string */
+		}else{
+			file_name = argv[i];
+			input = fopen(file_name, "r");
+			if(input == NULL)
+				error(FILE_ACCESS, argv[0], file_name);
+		}
+
+		/* print input to output */
+		if(file_copy(input, output))
+			error(FILE_WRITE, argv[0], STDOUT_NAME);
+
+		/* close input file if it's not stdin */
+		if(input != stdin && fclose(input))
+			error(FILE_CLOSE, argv[0], file_name);
+	}
+
+	/* exit successfully */
+	return 0;
+}

homepage/knowledge/cat/index.html

@@ -60,8 +60,8 @@ window.load_highlighting = function(language){
 }
 </SCRIPT>
 
-<H1>POSIX cat(1) WIP ARTICLE</H1>
-<H3>updated 2021-06-21</H3>
+<H1>POSIX cat(1)</H1>
+<H3>updated 2021-08-06</H3>
 <HR ALIGN="left" SIZE="1" WIDTH="25%" />
 <P><CODE>cat</CODE> on a POSIX or otherwise UNIX-like system is a program that exists to concatenate files; to “join” one file at its end to another at its start, and output that resulting file to standard output.</P>
 <P><CODE>cat</CODE> was introduced in UNIX v1 to supercede the program pr which printed the contents of a single file to the screen (McIlroy); its first-edition manual page described cat as “about the easiest way to print a file” (“cat(1)”). <CODE>cat</CODE>’s modern, typical use is more or less the same; it’s often introduced to UNIX beginners as a method to print the contents of a file to the screen, which is why many implementations of <CODE>cat</CODE> include options that are technically redundant - see the often-included <CODE>cat</CODE> <CODE>-e</CODE>, <CODE>-t</CODE>, and <CODE>-v</CODE> that replace the ends of lines, tabs, and invisible characters respectively with printing portrayals (“cat(1p)”).</P>
@@ -73,20 +73,31 @@ window.load_highlighting = function(language){
 #include &lt;stdlib.h&gt;
 #include &lt;string.h&gt;
 
-#define STDIN_NAME "&lt;stdin&gt;"
-#define STDOUT_NAME "&lt;stdout&gt;"
+#define STDIN_NAME &quot;&lt;stdin&gt;&quot;
+#define STDOUT_NAME &quot;&lt;stdout&gt;&quot;
 
-/* these two errors will exit out of the program with an unsuccessful status,
- * and print a diagnostic message to standard error */
+/* these are the predicted errors that could occur */
+enum error_type{
+	FILE_ACCESS,
+	FILE_CLOSE,
+	FILE_WRITE
+};
+
+/* this is an error function that will print to standard error the error that
+ * occurred in the program and exit */
 void
-file_access_error(char *argv0, char *file_name){
-	fprintf(stderr, "%s: %s: cannot open file\n", argv0, file_name);
-	exit(1);
+error(enum error_type type, char *argv0, char *file_name){
+	switch(type){
+	case FILE_ACCESS:
+		fprintf(stderr, &quot;%s: %s: cannot open file\n&quot;, argv0, file_name);
+		break;
+	case FILE_CLOSE:
+		fprintf(stderr, &quot;%s: %s: cannot close file\n&quot;, argv0, file_name);
+		break;
+	case FILE_WRITE:
+		fprintf(stderr, &quot;%s: %s: cannot write to file\n&quot;, argv0, file_name);
+		break;
 	}
-
-void
-file_write_error(char *argv0, char *file_name){
-	fprintf(stderr, "%s: %s: error writing to file\n", argv0, file_name);
 	exit(1);
 }
 
@@ -121,7 +132,7 @@ main(int argc, char *argv[]){
 
 	/* usage with 0 arguments - print standard input to standard output */
 	if(argc == 1 &amp;&amp; file_copy(stdin, stdout))
-		file_write_error(argv[0], STDOUT_NAME);
+		error(FILE_WRITE, argv[0], STDOUT_NAME);
 	else if(argc == 1)
 		return 0;
 
@@ -130,16 +141,16 @@ main(int argc, char *argv[]){
 
 		/* after `--`, interpret `--`, `-`, and `-u` as literal
 		 * filenames */
-		if(parsing_opts &amp;&amp; !strcmp(argv[i], "--")){
+		if(parsing_opts &amp;&amp; !strcmp(argv[i], &quot;--&quot;)){
 			parsing_opts = 0;
 			continue;
 
 		/* ignore `-u` if still parsing options */
-		}else if(parsing_opts &amp;&amp; !strcmp(argv[i], "-u"))
+		}else if(parsing_opts &amp;&amp; !strcmp(argv[i], &quot;-u&quot;))
 			continue;
 
 		/* take `-` to mean standard input if still parsing options */
-		else if(parsing_opts &amp;&amp; !strcmp(argv[i], "-")){
+		else if(parsing_opts &amp;&amp; !strcmp(argv[i], &quot;-&quot;)){
 			file_name = stdin_file_name;
 			input = stdin;
 
@@ -147,14 +158,18 @@ main(int argc, char *argv[]){
 		 * the right string */
 		}else{
 			file_name = argv[i];
-			input = fopen(file_name, "r");
+			input = fopen(file_name, &quot;r&quot;);
 			if(input == NULL)
-				file_access_error(argv[0], file_name);
+				error(FILE_ACCESS, argv[0], file_name);
 		}
 
 		/* print input to output */
 		if(file_copy(input, output))
-			file_write_error(argv[0], STDOUT_NAME);
+			error(FILE_WRITE, argv[0], STDOUT_NAME);
+
+		/* close input file if it's not stdin */
+		if(input != stdin &amp;&amp; fclose(input))
+			error(FILE_CLOSE, argv[0], file_name);
 	}
 
 	/* exit successfully */
@@ -162,6 +177,9 @@ main(int argc, char *argv[]){
 }
 </CODE></PRE>
 
+<P>
+This is also available at <A HREF="/knowledge/cat/cat.c">/knowledge/cat/cat.c on this website</A> as a plain .c file with which you can toy.
+</P>
 <P>It’s worth noting that this concept of cat as a utility that sequentially prints given files to standard output means <CODE>cat</CODE> can be replaced by a simple shell script that does the same using <CODE>dd</CODE> and <CODE>printf</CODE>; <CODE>cat</CODE> as defined by POSIX is actually totally redundant to other POSIX utilities. Here’s the shell script:</P>
 <INPUT ID="shell_toggle" ONCLICK="window.load_highlighting('shell');" TYPE="button" VALUE="Press this button to enable syntax highlighting within this code." />
 <PRE><CODE CLASS="language-shell" DATA-LANG="shell">
@@ -208,9 +226,16 @@ done
 exit 0
 </CODE></PRE>
 
-<P>It's worth noting that the <CODE>dd_</CODE> shell function in the above sample that allows for re-aliasing of <CODE>dd</CODE> to <CODE>dd bs=1</CODE> could be replaced with a shell variable <CODE>$DD</CODE> with the initial value <CODE>dd</CODE> and a changed value according to <CODE>-u</CODE> of <CODE>dd bs=1</CODE>. However, <CODE>alias dd="dd bs=1"</CODE> would not work due to how shell aliases are parsed (ShellCheck).</P>
+<P>
+It's worth noting that the <CODE>dd_</CODE> shell function in the above sample that allows for re-aliasing of <CODE>dd</CODE> to <CODE>dd bs=1</CODE> could be replaced with a shell variable <CODE>$DD</CODE> with the initial value <CODE>dd</CODE> and a changed value according to <CODE>-u</CODE> of <CODE>dd bs=1</CODE>.
+However, <CODE>alias dd="dd bs=1"</CODE> would not work due to how shell aliases are parsed (ShellCheck).
+</P>
 
-<P><CODE>cat</CODE> doesn't work well as a shell script though. The script is relatively slow for short files and very slow for very large files (though <CODE>dd</CODE> itself should probably be used to copy large files from one medium to another anyway). This is provided for educational purposes (though I personally use this shell script in my system PATH; the C implementation provided compiles to a much larger binary using gcc 11.1.0, so this saves a couple kilobytes).</P>
+<P>
+<CODE>cat</CODE> doesn't work well as a shell script though.
+The script is relatively slow for short files and very slow for very large files (though <CODE>dd</CODE> itself should probably be used to copy large files from one medium to another anyway).
+This is provided for educational purposes.
+</P>
 
 <H2>Cited media and further reading</H2><UL>
 	<LI>Articles<UL>