Revert "remove sfeed_tail: the standard tail -f can (soon) be used"

This reverts commit 7f3a45b0031ec9cababf764f7826e21bbb59e258.

3 files changed, 234 insertions, 0 deletions

diff --git a/Makefile b/Makefile
index 80b1a54..c13c801 100644
--- a/Makefile
+++ b/Makefile
@@ -10,6 +10,7 @@ BIN = \
 	sfeed_mbox\
 	sfeed_opml_import\
 	sfeed_plain\
+	sfeed_tail\
 	sfeed_web\
 	sfeed_xmlenc
 SCRIPTS = \
@@ -18,6 +19,7 @@ SCRIPTS = \
 
 SRC = ${BIN:=.c}
 HDR = \
+	tree.h\
 	util.h\
 	xml.h
 
diff --git a/sfeed_tail.1 b/sfeed_tail.1
new file mode 100644
index 0000000..a64aca1
--- /dev/null
+++ b/sfeed_tail.1
@@ -0,0 +1,48 @@
+.Dd January 29, 2016
+.Dt SFEED_TAIL 1
+.Os
+.Sh NAME
+.Nm sfeed_tail
+.Nd format unseen feed data to a plain-text list
+.Sh SYNOPSIS
+.Nm
+.Op Ar file...
+.Sh DESCRIPTION
+.Nm
+formats unseen feed data (TSV) from
+.Xr sfeed 1
+from stdin or
+.Ar file
+to stdout as a plain-text list.
+If one or more
+.Ar file
+are specified, the basename of the
+.Ar file
+is used as the feed name in the output.
+If no
+.Ar file
+parameters are specified and so the data is read from stdin the feed name
+is empty.
+.Pp
+.Nm
+will mark the initial items on the first run as seen.
+Then it will print the initial items if data is read from stdin, if the data
+is read on the first run by specifying the argument(s)
+.Ar file
+it will not show the initial seen items.
+.Pp
+Unseen items are printed per line in a similar format to
+.Xr sfeed_plain 1 ,
+duplicate items are ignored.
+The list of unique items is determined by the fields: feedname, item id and
+UNIX timestamp of the item date.
+.Sh IMPLEMENTATION NOTES
+Keep in mind that because
+.Nm
+keeps a list of all the items it can consume much memory.
+.Sh SEE ALSO
+.Xr sfeed 1 ,
+.Xr sfeed_plain 1 ,
+.Xr tail 1
+.Sh AUTHORS
+.An Hiltjo Posthuma Aq Mt hiltjo@codemadness.org
diff --git a/sfeed_tail.c b/sfeed_tail.c
new file mode 100644
index 0000000..cf0a0ba
--- /dev/null
+++ b/sfeed_tail.c
@@ -0,0 +1,184 @@
+#include <ctype.h>
+#include <err.h>
+#include <locale.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "tree.h"
+#include "util.h"
+
+static int firsttime;
+static int sleepsecs;
+static char *line;
+static size_t linesize;
+time_t comparetime;
+
+struct line {
+	char *id;
+	char *link;
+	char *title;
+	time_t timestamp;
+	RB_ENTRY(line) entry;
+};
+
+int
+linecmp(struct line *e1, struct line *e2)
+{
+	int r;
+
+	if ((r = strcmp(e1->id, e2->id)))
+		return r;
+	else if ((r = strcmp(e1->title, e2->title)))
+		return r;
+	return strcmp(e1->link, e2->link);
+}
+RB_HEAD(linetree, line) head = RB_INITIALIZER(&head);
+RB_GENERATE_STATIC(linetree, line, entry, linecmp)
+
+/* remove old entries from the tree that won't be shown anyway. */
+static void
+gc(void)
+{
+	struct line *line, *tmp;
+
+	RB_FOREACH_SAFE(line, linetree, &head, tmp) {
+		if (line->timestamp < comparetime) {
+/*			printf("DEBUG: gc: removing: %s %s\n",
+				line->id, line->title);*/
+			free(line->id);
+			free(line->link);
+			free(line->title);
+			RB_REMOVE(linetree, &head, line);
+			free(line);
+		}
+	}
+}
+
+static void
+printfeed(FILE *fp, const char *feedname)
+{
+	struct line *add, search;
+	char *fields[FieldLast], *s;
+	ssize_t linelen;
+	time_t parsedtime;
+	struct tm *tm;
+	int i;
+
+	while ((linelen = getline(&line, &linesize, fp)) > 0) {
+		if (line[linelen - 1] == '\n')
+			line[--linelen] = '\0';
+
+		if (!parseline(line, fields))
+			break;
+		parsedtime = 0;
+		if (strtotime(fields[FieldUnixTimestamp], &parsedtime))
+			continue;
+		if (!(tm = localtime(&parsedtime)))
+			err(1, "localtime");
+
+		/* old news: skip */
+		if (parsedtime < comparetime)
+			continue;
+
+		search.id = fields[FieldId];
+		search.link = fields[FieldLink];
+		search.title = fields[FieldTitle];
+		search.timestamp = parsedtime;
+		if (RB_FIND(linetree, &head, &search))
+			continue;
+
+/*		printf("DEBUG: new: id: %s, link: %s, title: %s\n",
+			fields[FieldId], fields[FieldLink], fields[FieldTitle]);*/
+
+		if (!(add = calloc(1, sizeof(*add))))
+			err(1, "calloc");
+		if (!(add->id = strdup(fields[FieldId])))
+			err(1, "strdup");
+		if (!(add->link = strdup(fields[FieldLink])))
+			err(1, "strdup");
+		if (!(add->title = strdup(fields[FieldTitle])))
+			err(1, "strdup");
+		add->timestamp = parsedtime;
+		RB_INSERT(linetree, &head, add);
+
+		if (firsttime)
+			continue;
+
+		/* output parsed line: it may not be the same as the input. */
+		for (i = 0; i < FieldLast; i++) {
+			if (i)
+				putchar('\t');
+			fputs(fields[i], stdout);
+		}
+		putchar('\n');
+		fflush(stdout);
+
+#if 0
+		if (fields[FieldFeedName][0])
+			printf("%-15.15s  ", fields[FieldFeedName]);
+		else if (feedname[0])
+			printf("%-15.15s  ", feedname);
+		printf("%04d-%02d-%02d %02d:%02d  ",
+		       tm->tm_year + 1900, tm->tm_mon + 1, tm->tm_mday,
+		       tm->tm_hour, tm->tm_min);
+		printutf8pad(stdout, fields[FieldTitle], 70, ' ');
+		printf(" %s\n", fields[FieldLink]);
+#endif
+	}
+}
+
+int
+main(int argc, char *argv[])
+{
+	char *name;
+	FILE *fp;
+	int i, slept = 0;
+
+	if (pledge("stdio rpath", NULL) == -1)
+		err(1, "pledge");
+
+	setlocale(LC_CTYPE, "");
+
+	if (pledge(argc == 1 ? "stdio" : "stdio rpath", NULL) == -1)
+		err(1, "pledge");
+
+	if (argc == 1)
+		sleepsecs = 1;
+	else
+		sleepsecs = 300;
+
+	for (firsttime = (argc > 1); ; firsttime = 0) {
+		if ((comparetime = time(NULL)) == -1)
+			err(1, "time");
+		/* 1 day is old news */
+		comparetime -= 86400;
+		if (argc == 1) {
+			printfeed(stdin, "");
+		} else {
+			for (i = 1; i < argc; i++) {
+				if (!(fp = fopen(argv[i], "r")))
+					err(1, "fopen: %s", argv[i]);
+				name = ((name = strrchr(argv[i], '/'))) ? name + 1 : argv[i];
+				printfeed(fp, name);
+				if (ferror(fp))
+					err(1, "ferror: %s", argv[i]);
+				fclose(fp);
+			}
+		}
+		// DEBUG: TODO: gc first run.
+		gc();
+
+		sleep(sleepsecs);
+		slept += sleepsecs;
+
+		/* gc once every hour (excluding run-time) */
+		if (slept >= 3600) {
+			gc();
+			slept = 0;
+		}
+	}
+	return 0;
+}