commit - 8477327a46979f9cfb839174a87ce51a085c3abd
commit + c15ce40c4456d3bb6d44092bb22097ad93768c3a
blob - /dev/null
blob + f09977b1a54d355b9b1d2d849dfac05e34f35590 (mode 644)
--- /dev/null
+++ src/cmd/file.c
+#include <u.h>
+#include <libc.h>
+#include <bio.h>
+#include <ctype.h>
+#include <mach.h>
+
+/*
+ * file - determine type of file
+ */
+#define LENDIAN(p) ((p)[0] | ((p)[1]<<8) | ((p)[2]<<16) | ((p)[3]<<24))
+
+uchar buf[6001];
+short cfreq[140];
+short wfreq[50];
+int nbuf;
+Dir* mbuf;
+int fd;
+char *fname;
+char *slash;
+
+enum
+{
+ Cword,
+ Fword,
+ Aword,
+ Alword,
+ Lword,
+ I1,
+ I2,
+ I3,
+ Clatin = 128,
+ Cbinary,
+ Cnull,
+ Ceascii,
+ Cutf,
+};
+struct
+{
+ char* word;
+ int class;
+} dict[] =
+{
+ "PATH", Lword,
+ "TEXT", Aword,
+ "adt", Alword,
+ "aggr", Alword,
+ "alef", Alword,
+ "array", Lword,
+ "block", Fword,
+ "chan", Alword,
+ "char", Cword,
+ "common", Fword,
+ "con", Lword,
+ "data", Fword,
+ "dimension", Fword,
+ "double", Cword,
+ "extern", Cword,
+ "bio", I2,
+ "float", Cword,
+ "fn", Lword,
+ "function", Fword,
+ "h", I3,
+ "implement", Lword,
+ "import", Lword,
+ "include", I1,
+ "int", Cword,
+ "integer", Fword,
+ "iota", Lword,
+ "libc", I2,
+ "long", Cword,
+ "module", Lword,
+ "real", Fword,
+ "ref", Lword,
+ "register", Cword,
+ "self", Lword,
+ "short", Cword,
+ "static", Cword,
+ "stdio", I2,
+ "struct", Cword,
+ "subroutine", Fword,
+ "u", I2,
+ "void", Cword,
+};
+
+/* codes for 'mode' field in language structure */
+enum {
+ Normal = 0,
+ First, /* first entry for language spanning several ranges */
+ Multi, /* later entries " " " ... */
+ Shared, /* codes used in several languages */
+ };
+
+struct
+{
+ int mode; /* see enum above */
+ int count;
+ int low;
+ int high;
+ char *name;
+
+} language[] =
+{
+ Normal, 0, 0x0080, 0x0080, "Extended Latin",
+ Normal, 0, 0x0100, 0x01FF, "Extended Latin",
+ Normal, 0, 0x0370, 0x03FF, "Greek",
+ Normal, 0, 0x0400, 0x04FF, "Cyrillic",
+ Normal, 0, 0x0530, 0x058F, "Armenian",
+ Normal, 0, 0x0590, 0x05FF, "Hebrew",
+ Normal, 0, 0x0600, 0x06FF, "Arabic",
+ Normal, 0, 0x0900, 0x097F, "Devanagari",
+ Normal, 0, 0x0980, 0x09FF, "Bengali",
+ Normal, 0, 0x0A00, 0x0A7F, "Gurmukhi",
+ Normal, 0, 0x0A80, 0x0AFF, "Gujarati",
+ Normal, 0, 0x0B00, 0x0B7F, "Oriya",
+ Normal, 0, 0x0B80, 0x0BFF, "Tamil",
+ Normal, 0, 0x0C00, 0x0C7F, "Telugu",
+ Normal, 0, 0x0C80, 0x0CFF, "Kannada",
+ Normal, 0, 0x0D00, 0x0D7F, "Malayalam",
+ Normal, 0, 0x0E00, 0x0E7F, "Thai",
+ Normal, 0, 0x0E80, 0x0EFF, "Lao",
+ Normal, 0, 0x1000, 0x105F, "Tibetan",
+ Normal, 0, 0x10A0, 0x10FF, "Georgian",
+ Normal, 0, 0x3040, 0x30FF, "Japanese",
+ Normal, 0, 0x3100, 0x312F, "Chinese",
+ First, 0, 0x3130, 0x318F, "Korean",
+ Multi, 0, 0x3400, 0x3D2F, "Korean",
+ Shared, 0, 0x4e00, 0x9fff, "CJK",
+ Normal, 0, 0, 0, 0, /* terminal entry */
+};
+
+
+enum
+{
+ Fascii, /* printable ascii */
+ Flatin, /* latin 1*/
+ Futf, /* UTf character set */
+ Fbinary, /* binary */
+ Feascii, /* ASCII with control chars */
+ Fnull, /* NULL in file */
+} guess;
+
+void bump_utf_count(Rune);
+int cistrncmp(char*, char*, int);
+void filetype(int);
+int getfontnum(uchar*, uchar**);
+int isas(void);
+int isc(void);
+int isenglish(void);
+int ishp(void);
+int ishtml(void);
+int isrfc822(void);
+int ismbox(void);
+int islimbo(void);
+int ismung(void);
+int isp9bit(void);
+int isp9font(void);
+int isrtf(void);
+int ismsdos(void);
+int iself(void);
+int istring(void);
+int iff(void);
+int long0(void);
+int istar(void);
+int p9bitnum(uchar*);
+int p9subfont(uchar*);
+void print_utf(void);
+void type(char*, int);
+int utf_count(void);
+void wordfreq(void);
+
+int (*call[])(void) =
+{
+ long0, /* recognizable by first 4 bytes */
+ istring, /* recognizable by first string */
+ iff, /* interchange file format (strings) */
+ isrfc822, /* email file */
+ ismbox, /* mail box */
+ istar, /* recognizable by tar checksum */
+ ishtml, /* html keywords */
+/* iscint, /* compiler/assembler intermediate */
+ islimbo, /* limbo source */
+ isc, /* c & alef compiler key words */
+ isas, /* assembler key words */
+ ismung, /* entropy compressed/encrypted */
+ isp9font, /* plan 9 font */
+ isp9bit, /* plan 9 image (as from /dev/window) */
+ isenglish, /* char frequency English */
+ isrtf, /* rich text format */
+ ismsdos, /* msdos exe (virus file attachement) */
+ iself, /* ELF (foreign) executable */
+ 0
+};
+
+int mime;
+
+#define OCTET "application/octet-stream\n"
+#define PLAIN "text/plain\n"
+
+void
+main(int argc, char *argv[])
+{
+ int i, j, maxlen;
+ char *cp;
+ Rune r;
+
+ ARGBEGIN{
+ case 'm':
+ mime = 1;
+ break;
+ default:
+ fprint(2, "usage: file [-m] [file...]\n");
+ exits("usage");
+ }ARGEND;
+
+ maxlen = 0;
+ if(mime == 0 || argc > 1){
+ for(i = 0; i < argc; i++) {
+ for (j = 0, cp = argv[i]; *cp; j++, cp += chartorune(&r, cp))
+ ;
+ if(j > maxlen)
+ maxlen = j;
+ }
+ }
+ if (argc <= 0) {
+ if(!mime)
+ print ("stdin: ");
+ filetype(0);
+ }
+ else {
+ for(i = 0; i < argc; i++)
+ type(argv[i], maxlen);
+ }
+ exits(0);
+}
+
+void
+type(char *file, int nlen)
+{
+ Rune r;
+ int i;
+ char *p;
+
+ if(nlen > 0){
+ slash = 0;
+ for (i = 0, p = file; *p; i++) {
+ if (*p == '/') /* find rightmost slash */
+ slash = p;
+ p += chartorune(&r, p); /* count runes */
+ }
+ print("%s:%*s",file, nlen-i+1, "");
+ }
+ fname = file;
+ if ((fd = open(file, OREAD)) < 0) {
+ print("cannot open\n");
+ return;
+ }
+ filetype(fd);
+ close(fd);
+}
+
+void
+filetype(int fd)
+{
+ Rune r;
+ int i, f, n;
+ char *p, *eob;
+
+ free(mbuf);
+ mbuf = dirfstat(fd);
+ if(mbuf == nil){
+ print("cannot stat: %r\n");
+ return;
+ }
+ if(mbuf->mode & DMDIR) {
+ print(mime ? "text/directory\n" : "directory\n");
+ return;
+ }
+ if(mbuf->type != 'M' && mbuf->type != '|') {
+ print(mime ? OCTET : "special file #%c/%s\n",
+ mbuf->type, mbuf->name);
+ return;
+ }
+ nbuf = read(fd, buf, sizeof(buf)-1);
+
+ if(nbuf < 0) {
+ print("cannot read\n");
+ return;
+ }
+ if(nbuf == 0) {
+ print(mime ? PLAIN : "empty file\n");
+ return;
+ }
+ buf[nbuf] = 0;
+
+ /*
+ * build histogram table
+ */
+ memset(cfreq, 0, sizeof(cfreq));
+ for (i = 0; language[i].name; i++)
+ language[i].count = 0;
+ eob = (char *)buf+nbuf;
+ for(n = 0, p = (char *)buf; p < eob; n++) {
+ if (!fullrune(p, eob-p) && eob-p < UTFmax)
+ break;
+ p += chartorune(&r, p);
+ if (r == 0)
+ f = Cnull;
+ else if (r <= 0x7f) {
+ if (!isprint(r) && !isspace(r))
+ f = Ceascii; /* ASCII control char */
+ else f = r;
+ } else if (r == 0x080) {
+ bump_utf_count(r);
+ f = Cutf;
+ } else if (r < 0xA0)
+ f = Cbinary; /* Invalid Runes */
+ else if (r <= 0xff)
+ f = Clatin; /* Latin 1 */
+ else {
+ bump_utf_count(r);
+ f = Cutf; /* UTF extension */
+ }
+ cfreq[f]++; /* ASCII chars peg directly */
+ }
+ /*
+ * gross classify
+ */
+ if (cfreq[Cbinary])
+ guess = Fbinary;
+ else if (cfreq[Cutf])
+ guess = Futf;
+ else if (cfreq[Clatin])
+ guess = Flatin;
+ else if (cfreq[Ceascii])
+ guess = Feascii;
+ else if (cfreq[Cnull] == n) {
+ print(mime ? OCTET : "first block all null bytes\n");
+ return;
+ }
+ else guess = Fascii;
+ /*
+ * lookup dictionary words
+ */
+ memset(wfreq, 0, sizeof(wfreq));
+ if(guess == Fascii || guess == Flatin || guess == Futf)
+ wordfreq();
+ /*
+ * call individual classify routines
+ */
+ for(i=0; call[i]; i++)
+ if((*call[i])())
+ return;
+
+ /*
+ * if all else fails,
+ * print out gross classification
+ */
+ if (nbuf < 100 && !mime)
+ print(mime ? PLAIN : "short ");
+ if (guess == Fascii)
+ print(mime ? PLAIN : "Ascii\n");
+ else if (guess == Feascii)
+ print(mime ? PLAIN : "extended ascii\n");
+ else if (guess == Flatin)
+ print(mime ? PLAIN : "latin ascii\n");
+ else if (guess == Futf && utf_count() < 4)
+ print_utf();
+ else print(mime ? OCTET : "binary\n");
+}
+
+void
+bump_utf_count(Rune r)
+{
+ int low, high, mid;
+
+ high = sizeof(language)/sizeof(language[0])-1;
+ for (low = 0; low < high;) {
+ mid = (low+high)/2;
+ if (r >=language[mid].low) {
+ if (r <= language[mid].high) {
+ language[mid].count++;
+ break;
+ } else low = mid+1;
+ } else high = mid;
+ }
+}
+
+int
+utf_count(void)
+{
+ int i, count;
+
+ count = 0;
+ for (i = 0; language[i].name; i++)
+ if (language[i].count > 0)
+ switch (language[i].mode) {
+ case Normal:
+ case First:
+ count++;
+ break;
+ default:
+ break;
+ }
+ return count;
+}
+
+int
+chkascii(void)
+{
+ int i;
+
+ for (i = 'a'; i < 'z'; i++)
+ if (cfreq[i])
+ return 1;
+ for (i = 'A'; i < 'Z'; i++)
+ if (cfreq[i])
+ return 1;
+ return 0;
+}
+
+int
+find_first(char *name)
+{
+ int i;
+
+ for (i = 0; language[i].name != 0; i++)
+ if (language[i].mode == First
+ && strcmp(language[i].name, name) == 0)
+ return i;
+ return -1;
+}
+
+void
+print_utf(void)
+{
+ int i, printed, j;
+
+ if(mime){
+ print(PLAIN);
+ return;
+ }
+ if (chkascii()) {
+ printed = 1;
+ print("Ascii");
+ } else
+ printed = 0;
+ for (i = 0; language[i].name; i++)
+ if (language[i].count) {
+ switch(language[i].mode) {
+ case Multi:
+ j = find_first(language[i].name);
+ if (j < 0)
+ break;
+ if (language[j].count > 0)
+ break;
+ /* Fall through */
+ case Normal:
+ case First:
+ if (printed)
+ print(" & ");
+ else printed = 1;
+ print("%s", language[i].name);
+ break;
+ case Shared:
+ default:
+ break;
+ }
+ }
+ if(!printed)
+ print("UTF");
+ print(" text\n");
+}
+
+void
+wordfreq(void)
+{
+ int low, high, mid, r;
+ uchar *p, *p2, c;
+
+ p = buf;
+ for(;;) {
+ while (p < buf+nbuf && !isalpha(*p))
+ p++;
+ if (p >= buf+nbuf)
+ return;
+ p2 = p;
+ while(p < buf+nbuf && isalpha(*p))
+ p++;
+ c = *p;
+ *p = 0;
+ high = sizeof(dict)/sizeof(dict[0]);
+ for(low = 0;low < high;) {
+ mid = (low+high)/2;
+ r = strcmp(dict[mid].word, (char*)p2);
+ if(r == 0) {
+ wfreq[dict[mid].class]++;
+ break;
+ }
+ if(r < 0)
+ low = mid+1;
+ else
+ high = mid;
+ }
+ *p++ = c;
+ }
+}
+
+typedef struct Filemagic Filemagic;
+struct Filemagic {
+ ulong x;
+ ulong mask;
+ char *desc;
+ char *mime;
+};
+
+Filemagic long0tab[] = {
+ 0xF16DF16D, 0xFFFFFFFF, "pac1 audio file\n", OCTET,
+ 0x31636170, 0xFFFFFFFF, "pac3 audio file\n", OCTET,
+ 0x32636170, 0xFFFF00FF, "pac4 audio file\n", OCTET,
+ 0xBA010000, 0xFFFFFFFF, "mpeg system stream\n", OCTET,
+ 0x30800CC0, 0xFFFFFFFF, "inferno .dis executable\n", OCTET,
+ 0x04034B50, 0xFFFFFFFF, "zip archive\n", "application/zip",
+ 070707, 0xFFFF, "cpio archive\n", OCTET,
+ 0x2F7, 0xFFFF, "tex dvi\n", "application/dvi",
+ 0xfffa0000, 0xfffe0000, "mp3 audio", "audio/mpeg",
+};
+
+int
+filemagic(Filemagic *tab, int ntab, ulong x)
+{
+ int i;
+
+ for(i=0; i<ntab; i++)
+ if((x&tab[i].mask) == tab[i].x){
+ print(mime ? tab[i].mime : tab[i].desc);
+ return 1;
+ }
+ return 0;
+}
+
+int
+long0(void)
+{
+// Fhdr *f;
+ long x;
+
+ seek(fd, 0, 0); /* reposition to start of file */
+/*
+ if(crackhdr(fd, &f)) {
+ print(mime ? OCTET : "%s\n", f.name);
+ return 1;
+ }
+*/
+ x = LENDIAN(buf);
+ if(filemagic(long0tab, nelem(long0tab), x))
+ return 1;
+ return 0;
+}
+
+/* from tar.c */
+enum { NAMSIZ = 100, TBLOCK = 512 };
+
+union hblock
+{
+ char dummy[TBLOCK];
+ struct header
+ {
+ char name[NAMSIZ];
+ char mode[8];
+ char uid[8];
+ char gid[8];
+ char size[12];
+ char mtime[12];
+ char chksum[8];
+ char linkflag;
+ char linkname[NAMSIZ];
+ /* rest are defined by POSIX's ustar format; see p1003.2b */
+ char magic[6]; /* "ustar" */
+ char version[2];
+ char uname[32];
+ char gname[32];
+ char devmajor[8];
+ char devminor[8];
+ char prefix[155]; /* if non-null, path = prefix "/" name */
+ } dbuf;
+};
+
+int
+checksum(union hblock *hp)
+{
+ int i;
+ char *cp;
+ struct header *hdr = &hp->dbuf;
+
+ for (cp = hdr->chksum; cp < &hdr->chksum[sizeof hdr->chksum]; cp++)
+ *cp = ' ';
+ i = 0;
+ for (cp = hp->dummy; cp < &hp->dummy[TBLOCK]; cp++)
+ i += *cp & 0xff;
+ return i;
+}
+
+int
+istar(void)
+{
+ int chksum;
+ char tblock[TBLOCK];
+ union hblock *hp = (union hblock *)tblock;
+ struct header *hdr = &hp->dbuf;
+
+ seek(fd, 0, 0); /* reposition to start of file */
+ if (readn(fd, tblock, sizeof tblock) != sizeof tblock)
+ return 0;
+ chksum = strtol(hdr->chksum, 0, 8);
+ if (hdr->name[0] != '\0' && checksum(hp) == chksum) {
+ if (strcmp(hdr->magic, "ustar") == 0)
+ print(mime? "application/x-ustar\n":
+ "posix tar archive\n");
+ else
+ print(mime? "application/x-tar\n": "tar archive\n");
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * initial words to classify file
+ */
+struct FILE_STRING
+{
+ char *key;
+ char *filetype;
+ int length;
+ char *mime;
+} file_string[] =
+{
+ "!<arch>\n__.SYMDEF", "archive random library", 16, "application/octet-stream",
+ "!<arch>\n", "archive", 8, "application/octet-stream",
+ "070707", "cpio archive - ascii header", 6, "application/octet-stream",
+ "#!/bin/rc", "rc executable file", 9, "text/plain",
+ "#!/bin/sh", "sh executable file", 9, "text/plain",
+ "%!", "postscript", 2, "application/postscript",
+ "\004%!", "postscript", 3, "application/postscript",
+ "x T post", "troff output for post", 8, "application/troff",
+ "x T Latin1", "troff output for Latin1", 10, "application/troff",
+ "x T utf", "troff output for UTF", 7, "application/troff",
+ "x T 202", "troff output for 202", 7, "application/troff",
+ "x T aps", "troff output for aps", 7, "application/troff",
+ "GIF", "GIF image", 3, "image/gif",
+ "\0PC Research, Inc\0", "ghostscript fax file", 18, "application/ghostscript",
+ "%PDF", "PDF", 4, "application/pdf",
+ "<html>\n", "HTML file", 7, "text/html",
+ "<HTML>\n", "HTML file", 7, "text/html",
+ "compressed\n", "Compressed image or subfont", 11, "application/octet-stream",
+ "\111\111\052\000", "tiff", 4, "image/tiff",
+ "\115\115\000\052", "tiff", 4, "image/tiff",
+ "\377\330\377\340", "jpeg", 4, "image/jpeg",
+ "\377\330\377\341", "jpeg", 4, "image/jpeg",
+ "\377\330\377\333", "jpeg", 4, "image/jpeg",
+ "BM", "bmp", 2, "image/bmp",
+ "\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1", "microsoft office document", 8, "application/octet-stream",
+ "<MakerFile ", "FrameMaker file", 11, "application/framemaker",
+ "\033%-12345X", "HPJCL file", 9, "application/hpjcl",
+ "ID3", "mp3 audio with id3", 3, "audio/mpeg",
+ 0,0,0,0
+};
+
+int
+istring(void)
+{
+ int i;
+ struct FILE_STRING *p;
+
+ for(p = file_string; p->key; p++) {
+ if(nbuf >= p->length && !memcmp(buf, p->key, p->length)) {
+ if(mime)
+ print("%s\n", p->mime);
+ else
+ print("%s\n", p->filetype);
+ return 1;
+ }
+ }
+ if(strncmp((char*)buf, "TYPE=", 5) == 0) { /* td */
+ for(i = 5; i < nbuf; i++)
+ if(buf[i] == '\n')
+ break;
+ if(mime)
+ print(OCTET);
+ else
+ print("%.*s picture\n", utfnlen((char*)buf+5, i-5), (char*)buf+5);
+ return 1;
+ }
+ return 0;
+}
+
+int
+iff(void)
+{
+ if (strncmp((char*)buf, "FORM", 4) == 0 &&
+ strncmp((char*)buf+8, "AIFF", 4) == 0) {
+ print("%s\n", mime? "audio/x-aiff": "aiff audio");
+ return 1;
+ }
+ return 0;
+}
+
+char* html_string[] =
+{
+ "title",
+ "body",
+ "head",
+ "strong",
+ "h1",
+ "h2",
+ "h3",
+ "h4",
+ "h5",
+ "h6",
+ "ul",
+ "li",
+ "dl",
+ "br",
+ "em",
+ 0,
+};
+
+int
+ishtml(void)
+{
+ uchar *p, *q;
+ int i, count;
+
+ /* compare strings between '<' and '>' to html table */
+ count = 0;
+ p = buf;
+ for(;;) {
+ while (p < buf+nbuf && *p != '<')
+ p++;
+ p++;
+ if (p >= buf+nbuf)
+ break;
+ if(*p == '/')
+ p++;
+ q = p;
+ while(p < buf+nbuf && *p != '>')
+ p++;
+ if (p >= buf+nbuf)
+ break;
+ for(i = 0; html_string[i]; i++) {
+ if(cistrncmp(html_string[i], (char*)q, p-q) == 0) {
+ if(count++ > 4) {
+ print(mime ? "text/html\n" : "HTML file\n");
+ return 1;
+ }
+ break;
+ }
+ }
+ p++;
+ }
+ return 0;
+}
+
+char* rfc822_string[] =
+{
+ "from:",
+ "date:",
+ "to:",
+ "subject:",
+ "received:",
+ "reply to:",
+ "sender:",
+ 0,
+};
+
+int
+isrfc822(void)
+{
+
+ char *p, *q, *r;
+ int i, count;
+
+ count = 0;
+ p = (char*)buf;
+ for(;;) {
+ q = strchr(p, '\n');
+ if(q == nil)
+ break;
+ *q = 0;
+ if(p == (char*)buf && strncmp(p, "From ", 5) == 0 && strstr(p, " remote from ")){
+ count++;
+ *q = '\n';
+ p = q+1;
+ continue;
+ }
+ *q = '\n';
+ if(*p != '\t' && *p != ' '){
+ r = strchr(p, ':');
+ if(r == 0 || r > q)
+ break;
+ for(i = 0; rfc822_string[i]; i++) {
+ if(cistrncmp(p, rfc822_string[i], strlen(rfc822_string[i])) == 0){
+ count++;
+ break;
+ }
+ }
+ }
+ p = q+1;
+ }
+ if(count >= 3){
+ print(mime ? "message/rfc822\n" : "email file\n");
+ return 1;
+ }
+ return 0;
+}
+
+int
+ismbox(void)
+{
+ char *p, *q;
+
+ p = (char*)buf;
+ q = strchr(p, '\n');
+ if(q == nil)
+ return 0;
+ *q = 0;
+ if(strncmp(p, "From ", 5) == 0 && strstr(p, " remote from ") == nil){
+ print(mime ? "text/plain\n" : "mail box\n");
+ return 1;
+ }
+ *q = '\n';
+ return 0;
+}
+
+int
+isc(void)
+{
+ int n;
+
+ n = wfreq[I1];
+ /*
+ * includes
+ */
+ if(n >= 2 && wfreq[I2] >= n && wfreq[I3] >= n && cfreq['.'] >= n)
+ goto yes;
+ if(n >= 1 && wfreq[Alword] >= n && wfreq[I3] >= n && cfreq['.'] >= n)
+ goto yes;
+ /*
+ * declarations
+ */
+ if(wfreq[Cword] >= 5 && cfreq[';'] >= 5)
+ goto yes;
+ /*
+ * assignments
+ */
+ if(cfreq[';'] >= 10 && cfreq['='] >= 10 && wfreq[Cword] >= 1)
+ goto yes;
+ return 0;
+
+yes:
+ if(mime){
+ print(PLAIN);
+ return 1;
+ }
+ if(wfreq[Alword] > 0)
+ print("alef program\n");
+ else
+ print("c program\n");
+ return 1;
+}
+
+int
+islimbo(void)
+{
+
+ /*
+ * includes
+ */
+ if(wfreq[Lword] < 4)
+ return 0;
+ print(mime ? PLAIN : "limbo program\n");
+ return 1;
+}
+
+int
+isas(void)
+{
+
+ /*
+ * includes
+ */
+ if(wfreq[Aword] < 2)
+ return 0;
+ print(mime ? PLAIN : "as program\n");
+ return 1;
+}
+
+/*
+ * low entropy means encrypted
+ */
+int
+ismung(void)
+{
+ int i, bucket[8];
+ float cs;
+
+ if(nbuf < 64)
+ return 0;
+ memset(bucket, 0, sizeof(bucket));
+ for(i=0; i<64; i++)
+ bucket[(buf[i]>>5)&07] += 1;
+
+ cs = 0.;
+ for(i=0; i<8; i++)
+ cs += (bucket[i]-8)*(bucket[i]-8);
+ cs /= 8.;
+ if(cs <= 24.322) {
+ if(buf[0]==0x1f && (buf[1]==0x8b || buf[1]==0x9d))
+ print(mime ? OCTET : "compressed\n");
+ else
+ print(mime ? OCTET : "encrypted\n");
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * english by punctuation and frequencies
+ */
+int
+isenglish(void)
+{
+ int vow, comm, rare, badpun, punct;
+ char *p;
+
+ if(guess != Fascii && guess != Feascii)
+ return 0;
+ badpun = 0;
+ punct = 0;
+ for(p = (char *)buf; p < (char *)buf+nbuf-1; p++)
+ switch(*p) {
+ case '.':
+ case ',':
+ case ')':
+ case '%':
+ case ';':
+ case ':':
+ case '?':
+ punct++;
+ if(p[1] != ' ' && p[1] != '\n')
+ badpun++;
+ }
+ if(badpun*5 > punct)
+ return 0;
+ if(cfreq['>']+cfreq['<']+cfreq['/'] > cfreq['e']) /* shell file test */
+ return 0;
+ if(2*cfreq[';'] > cfreq['e'])
+ return 0;
+
+ vow = 0;
+ for(p="AEIOU"; *p; p++) {
+ vow += cfreq[*p];
+ vow += cfreq[tolower(*p)];
+ }
+ comm = 0;
+ for(p="ETAION"; *p; p++) {
+ comm += cfreq[*p];
+ comm += cfreq[tolower(*p)];
+ }
+ rare = 0;
+ for(p="VJKQXZ"; *p; p++) {
+ rare += cfreq[*p];
+ rare += cfreq[tolower(*p)];
+ }
+ if(vow*5 >= nbuf-cfreq[' '] && comm >= 10*rare) {
+ print(mime ? PLAIN : "English text\n");
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * pick up a number with
+ * syntax _*[0-9]+_
+ */
+#define P9BITLEN 12
+int
+p9bitnum(uchar *bp)
+{
+ int n, c, len;
+
+ len = P9BITLEN;
+ while(*bp == ' ') {
+ bp++;
+ len--;
+ if(len <= 0)
+ return -1;
+ }
+ n = 0;
+ while(len > 1) {
+ c = *bp++;
+ if(!isdigit(c))
+ return -1;
+ n = n*10 + c-'0';
+ len--;
+ }
+ if(*bp != ' ')
+ return -1;
+ return n;
+}
+
+int
+depthof(char *s, int *newp)
+{
+ char *es;
+ int d;
+
+ *newp = 0;
+ es = s+12;
+ while(s<es && *s==' ')
+ s++;
+ if(s == es)
+ return -1;
+ if('0'<=*s && *s<='9')
+ return 1<<atoi(s);
+
+ *newp = 1;
+ d = 0;
+ while(s<es && *s!=' '){
+ s++; /* skip letter */
+ d += strtoul(s, &s, 10);
+ }
+
+ switch(d){
+ case 32:
+ case 24:
+ case 16:
+ case 8:
+ return d;
+ }
+ return -1;
+}
+
+int
+isp9bit(void)
+{
+ int dep, lox, loy, hix, hiy, px, new;
+ ulong t;
+ long len;
+ char *newlabel;
+
+ newlabel = "old ";
+
+ dep = depthof((char*)buf + 0*P9BITLEN, &new);
+ if(new)
+ newlabel = "";
+ lox = p9bitnum(buf + 1*P9BITLEN);
+ loy = p9bitnum(buf + 2*P9BITLEN);
+ hix = p9bitnum(buf + 3*P9BITLEN);
+ hiy = p9bitnum(buf + 4*P9BITLEN);
+ if(dep < 0 || lox < 0 || loy < 0 || hix < 0 || hiy < 0)
+ return 0;
+
+ if(dep < 8){
+ px = 8/dep; /* pixels per byte */
+ /* set l to number of bytes of data per scan line */
+ if(lox >= 0)
+ len = (hix+px-1)/px - lox/px;
+ else{ /* make positive before divide */
+ t = (-lox)+px-1;
+ t = (t/px)*px;
+ len = (t+hix+px-1)/px;
+ }
+ }else
+ len = (hix-lox)*dep/8;
+ len *= (hiy-loy); /* col length */
+ len += 5*P9BITLEN; /* size of initial ascii */
+
+ /*
+ * for image file, length is non-zero and must match calculation above
+ * for /dev/window and /dev/screen the length is always zero
+ * for subfont, the subfont header should follow immediately.
+ */
+ if (len != 0 && mbuf->length == 0) {
+ print("%splan 9 image\n", newlabel);
+ return 1;
+ }
+ if (mbuf->length == len) {
+ print("%splan 9 image\n", newlabel);
+ return 1;
+ }
+ /* Ghostscript sometimes produces a little extra on the end */
+ if (mbuf->length < len+P9BITLEN) {
+ print("%splan 9 image\n", newlabel);
+ return 1;
+ }
+ if (p9subfont(buf+len)) {
+ print("%ssubfont file\n", newlabel);
+ return 1;
+ }
+ return 0;
+}
+
+int
+p9subfont(uchar *p)
+{
+ int n, h, a;
+
+ /* if image too big, assume it's a subfont */
+ if (p+3*P9BITLEN > buf+sizeof(buf))
+ return 1;
+
+ n = p9bitnum(p + 0*P9BITLEN); /* char count */
+ if (n < 0)
+ return 0;
+ h = p9bitnum(p + 1*P9BITLEN); /* height */
+ if (h < 0)
+ return 0;
+ a = p9bitnum(p + 2*P9BITLEN); /* ascent */
+ if (a < 0)
+ return 0;
+ return 1;
+}
+
+#define WHITESPACE(c) ((c) == ' ' || (c) == '\t' || (c) == '\n')
+
+int
+isp9font(void)
+{
+ uchar *cp, *p;
+ int i, n;
+ char pathname[1024];
+
+ cp = buf;
+ if (!getfontnum(cp, &cp)) /* height */
+ return 0;
+ if (!getfontnum(cp, &cp)) /* ascent */
+ return 0;
+ for (i = 0; 1; i++) {
+ if (!getfontnum(cp, &cp)) /* min */
+ break;
+ if (!getfontnum(cp, &cp)) /* max */
+ return 0;
+ while (WHITESPACE(*cp))
+ cp++;
+ for (p = cp; *cp && !WHITESPACE(*cp); cp++)
+ ;
+ /* construct a path name, if needed */
+ n = 0;
+ if (*p != '/' && slash) {
+ n = slash-fname+1;
+ if (n < sizeof(pathname))
+ memcpy(pathname, fname, n);
+ else n = 0;
+ }
+ if (n+cp-p < sizeof(pathname)) {
+ memcpy(pathname+n, p, cp-p);
+ n += cp-p;
+ pathname[n] = 0;
+ if (access(pathname, AEXIST) < 0)
+ return 0;
+ }
+ }
+ if (i) {
+ print(mime ? "text/plain\n" : "font file\n");
+ return 1;
+ }
+ return 0;
+}
+
+int
+getfontnum(uchar *cp, uchar **rp)
+{
+ while (WHITESPACE(*cp)) /* extract ulong delimited by whitespace */
+ cp++;
+ if (*cp < '0' || *cp > '9')
+ return 0;
+ strtoul((char *)cp, (char **)rp, 0);
+ if (!WHITESPACE(**rp))
+ return 0;
+ return 1;
+}
+
+int
+isrtf(void)
+{
+ if(strstr((char *)buf, "\\rtf1")){
+ print(mime ? "application/rtf\n" : "rich text format\n");
+ return 1;
+ }
+ return 0;
+}
+
+int
+ismsdos(void)
+{
+ if (buf[0] == 0x4d && buf[1] == 0x5a){
+ print(mime ? "application/x-msdownload\n" : "MSDOS executable\n");
+ return 1;
+ }
+ return 0;
+}
+
+int
+iself(void)
+{
+ char *cpu[] = { /* NB: incomplete and arbitary list */
+ [1] "WE32100",
+ [2] "SPARC",
+ [3] "i386",
+ [4] "M68000",
+ [5] "M88000",
+ [6] "i486",
+ [7] "i860",
+ [8] "R3000",
+ [9] "S370",
+ [10] "R4000",
+ [15] "HP-PA",
+ [18] "sparc v8+",
+ [19] "i960",
+ [20] "PPC-32",
+ [21] "PPC-64",
+ [40] "ARM",
+ [41] "Alpha",
+ [43] "sparc v9",
+ [50] "IA-46",
+ [62] "AMD64",
+ [75] "VAX",
+ };
+
+
+ if (memcmp(buf, "\x7fELF", 4) == 0){
+ if (!mime){
+ int n = (buf[19] << 8) | buf[18];
+ char *p = "unknown";
+
+ if (n > 0 && n < nelem(cpu) && cpu[n])
+ p = cpu[n];
+ else {
+ /* try the other byte order */
+ n = (buf[18] << 8) | buf[19];
+ if (n > 0 && n < nelem(cpu) && cpu[n])
+ p = cpu[n];
+ }
+ print("%s ELF executable\n", p);
+ }
+ else
+ print("application/x-elf-executable");
+ return 1;
+ }
+
+ return 0;
+}
blob - /dev/null
blob + 3fb60ac66c790f5c14c5a8fa69630c10c2bac7d3 (mode 644)
--- /dev/null
+++ src/cmd/postscript/text2post/mkfile
+<$PLAN9/src/mkhdr
+
+<../config
+
+COMMONDIR=../common
+
+TARG=text2post
+
+OFILES=text2post.$O\
+
+HFILES=$COMMONDIR/comments.h\
+ $COMMONDIR/path.h\
+
+BIN=$POSTBIN
+<$PLAN9/src/mkone
+
+CFLAGS=-c -D'PROGRAMVERSION="0.1"' -D'DOROUND=1' -I$COMMONDIR
+
+install:V: $POSTLIB/pjw.char.ps
+
+$POSTLIB/pjw.char.ps: pjw.char.ps
+ cp $prereq $target
+
blob - /dev/null
blob + 5530861894ae0f66dc9e565e126a72d9f39d8cdf (mode 644)
--- /dev/null
+++ src/cmd/postscript/text2post/pjw.char.ps
+%!PS-Adobe-3.0 EPSF-3.0
+%%BoundingBox: 1 -1 199 258
+%%Creator: MetaPost
+%%CreationDate: 1994.06.28:1046
+/pjw1 {
+37 211 moveto
+37 206 lineto
+41 206 lineto
+43 212 lineto
+44 212 46 212 46 210 curveto
+41 198 35 186 35 174 curveto
+50 174 66 175 81 173 curveto
+81 171 lineto
+61 171 lineto
+61 170 lineto
+86 170 lineto
+88 168 89 166 90 164 curveto
+101 164 111 169 122 172 curveto
+139 172 lineto
+125 194 115 219 93 233 curveto
+87 234 80 236 74 235 curveto
+64 229 54 224 46 217 curveto
+45 217 44 217 44 218 curveto
+61 242 lineto
+67 248 72 258 82 258 curveto
+94 257 107 256 119 254 curveto
+134 247 147 239 161 231 curveto
+180 231 lineto
+180 226 174 228 171 226 curveto
+178 220 185 214 192 207 curveto
+189 207 187 207 187 205 curveto
+190 205 193 204 196 203 curveto
+198 193 202 181 193 181 curveto
+193 177 198 175 198 171 curveto
+196 171 194 171 194 169 curveto
+195 165 196 161 198 157 curveto
+194 147 193 135 184 130 curveto
+180 130 lineto
+169 107 lineto
+171 103 176 104 180 104 curveto
+180 93 176 81 166 76 curveto
+162 76 157 77 155 80 curveto
+153 80 152 80 151 80 curveto
+151 71 lineto
+155 71 lineto
+155 68 153 65 152 63 curveto
+145 62 lineto
+141 47 144 31 144 15 curveto
+141 0 lineto
+124 0 107 -1 90 1 curveto
+72 36 lineto
+86 48 105 49 122 54 curveto
+122 54 lineto
+110 61 97 65 84 69 curveto
+81 71 78 73 78 76 curveto
+86 77 93 77 101 77 curveto
+106 79 113 79 113 84 curveto
+95 86 77 87 59 89 curveto
+59 92 61 95 64 95 curveto
+69 88 80 92 89 92 curveto
+95 92 104 90 104 96 curveto
+93 97 lineto
+87 103 82 109 77 115 curveto
+89 116 101 117 113 118 curveto
+99 154 lineto
+90 154 87 144 82 138 curveto
+77 132 73 124 66 120 curveto
+63 120 59 119 59 122 curveto
+62 123 66 123 66 126 curveto
+58 126 50 127 42 128 curveto
+34 137 lineto
+34 140 34 144 31 144 curveto
+30 135 31 125 31 116 curveto
+25 116 22 122 19 127 curveto
+16 131 15 136 12 139 curveto
+5 139 15 127 9 127 curveto
+3 133 3 142 1 150 curveto
+1 158 6 166 9 173 curveto
+18 186 25 199 35 211 curveto
+closepath
+} bind def
+
+/pjw2 {
+27 112 moveto
+40 75 lineto
+40 74 38 73 37 73 curveto
+25 87 lineto
+17 112 lineto
+closepath
+43 154 moveto
+43 167 lineto
+41 167 38 167 39 169 curveto
+57 171 lineto
+74 167 lineto
+74 166 73 165 72 165 curveto
+64 164 56 162 49 158 curveto
+48 154 45 149 49 149 curveto
+51 151 53 152 55 154 curveto
+87 153 lineto
+87 144 80 136 74 129 curveto
+64 128 53 126 43 129 curveto
+37 135 lineto
+37 138 36 141 36 145 curveto
+40 145 lineto
+41 148 42 151 43 154 curveto closepath
+108 145 moveto
+119 145 130 143 141 140 curveto
+146 134 155 129 149 126 curveto
+138 124 126 123 116 129 curveto
+113 134 108 139 108 145 curveto
+closepath
+114 96 moveto
+116 103 118 110 121 117 curveto
+128 117 134 112 139 107 curveto
+139 101 137 96 132 93 curveto
+closepath
+134 162 moveto
+115 162 lineto
+115 162 115 163 115 164 curveto
+134 164 lineto
+closepath
+117 73 moveto
+115 78 121 81 125 85 curveto
+129 85 lineto
+130 83 131 81 131 79 curveto
+128 74 lineto
+124 74 121 73 117 73 curveto closepath
+141 119 moveto
+134 119 126 117 126 123 curveto
+131 123 136 122 141 121 curveto
+closepath
+} bind def
+
+/pw {
+%% pop
+gsave
+pointsize .0022 mul dup scale
+currentpoint translate
+ pjw1 pjw2 eofill
+grestore
+6 0 rmoveto
+} bind def
blob - /dev/null
blob + cf6b109e4685dcca21bb823593a1313b4a427937 (mode 644)
--- /dev/null
+++ src/cmd/postscript/text2post/text2post.c
+#include <u.h>
+#include <libc.h>
+#include <ctype.h>
+#include <bio.h>
+#include <comments.h>
+#include <path.h>
+
+#define UNKNOWNCHAR unsharp("#9/postscript/prologues/pjw.char.ps")
+
+char *optnames = "a:c:f:l:m:n:o:p:s:t:x:y:P:";
+
+Biobuf *bstdin, *bstdout, *bstderr;
+Biobuf *Bstdin, *Bstdout, *Bstderr;
+int char_no = 0; /* character to be done on a line */
+int line_no = 0; /* line number on a page */
+int page_no = 0; /* page number in a document */
+int in_string; /* Boolean, to know whether or not we are inside a Postscript string */
+int spaces = 0;
+int tabs = 0;
+int pages_printed;
+double aspectratio = 1.0;
+int copies = 1;
+double magnification = 1.0;
+int landscape = 0;
+int formsperpage = 1;
+int linesperpage = 66;
+int pointsize = 10;
+double xoffset = .25;
+double yoffset = .25;
+char *passthrough = 0;
+static int pplistmaxsize=0;
+
+unsigned char *pplist=0; /* bitmap list for storing pages to print */
+
+struct strtab {
+ int size;
+ char *str;
+ int used;
+};
+
+struct strtab charcode[256] = {
+ {4, "\\000"}, {4, "\\001"}, {4, "\\002"}, {4, "\\003"},
+ {4, "\\004"}, {4, "\\005"}, {4, "\\006"}, {4, "\\007"},
+ {4, "\\010"}, {4, "\\011"}, {4, "\\012"}, {4, "\\013"},
+ {4, "\\014"}, {4, "\\015"}, {4, "\\016"}, {4, "\\017"},
+ {4, "\\020"}, {4, "\\021"}, {4, "\\022"}, {4, "\\023"},
+ {4, "\\024"}, {4, "\\025"}, {4, "\\026"}, {4, "\\027"},
+ {4, "\\030"}, {4, "\\031"}, {4, "\\032"}, {4, "\\033"},
+ {4, "\\034"}, {4, "\\035"}, {4, "\\036"}, {4, "\\037"},
+ {1, " "}, {1, "!"}, {1, "\""}, {1, "#"},
+ {1, "$"}, {1, "%"}, {1, "&"}, {1, "'"},
+ {2, "\\("}, {2, "\\)"}, {1, "*"}, {1, "+"},
+ {1, ","}, {1, "-"}, {1, "."}, {1, "/"},
+ {1, "0"}, {1, "1"}, {1, "2"}, {1, "3"},
+ {1, "4"}, {1, "5"}, {1, "6"}, {1, "7"},
+ {1, "8"}, {1, "9"}, {1, ":"}, {1, ";"},
+ {1, "<"}, {1, "="}, {1, ">"}, {1, "?"},
+ {1, "@"}, {1, "A"}, {1, "B"}, {1, "C"},
+ {1, "D"}, {1, "E"}, {1, "F"}, {1, "G"},
+ {1, "H"}, {1, "I"}, {1, "J"}, {1, "K"},
+ {1, "L"}, {1, "M"}, {1, "N"}, {1, "O"},
+ {1, "P"}, {1, "Q"}, {1, "R"}, {1, "S"},
+ {1, "T"}, {1, "U"}, {1, "V"}, {1, "W"},
+ {1, "X"}, {1, "Y"}, {1, "Z"}, {1, "["},
+ {2, "\\\\"}, {1, "]"}, {1, "^"}, {1, "_"},
+ {1, "`"}, {1, "a"}, {1, "b"}, {1, "c"},
+ {1, "d"}, {1, "e"}, {1, "f"}, {1, "g"},
+ {1, "h"}, {1, "i"}, {1, "j"}, {1, "k"},
+ {1, "l"}, {1, "m"}, {1, "n"}, {1, "o"},
+ {1, "p"}, {1, "q"}, {1, "r"}, {1, "s"},
+ {1, "t"}, {1, "u"}, {1, "v"}, {1, "w"},
+ {1, "x"}, {1, "y"}, {1, "z"}, {1, "{"},
+ {1, "|"}, {1, "}"}, {1, "~"}, {4, "\\177"},
+ {4, "\\200"}, {4, "\\201"}, {4, "\\202"}, {4, "\\203"},
+ {4, "\\204"}, {4, "\\205"}, {4, "\\206"}, {4, "\\207"},
+ {4, "\\210"}, {4, "\\211"}, {4, "\\212"}, {4, "\\213"},
+ {4, "\\214"}, {4, "\\215"}, {4, "\\216"}, {4, "\\217"},
+ {4, "\\220"}, {4, "\\221"}, {4, "\\222"}, {4, "\\223"},
+ {4, "\\224"}, {4, "\\225"}, {4, "\\226"}, {4, "\\227"},
+ {4, "\\230"}, {4, "\\231"}, {4, "\\232"}, {4, "\\233"},
+ {4, "\\234"}, {4, "\\235"}, {4, "\\236"}, {4, "\\237"},
+ {4, "\\240"}, {4, "\\241"}, {4, "\\242"}, {4, "\\243"},
+ {4, "\\244"}, {4, "\\245"}, {4, "\\246"}, {4, "\\247"},
+ {4, "\\250"}, {4, "\\251"}, {4, "\\252"}, {4, "\\253"},
+ {4, "\\254"}, {4, "\\255"}, {4, "\\256"}, {4, "\\257"},
+ {4, "\\260"}, {4, "\\261"}, {4, "\\262"}, {4, "\\263"},
+ {4, "\\264"}, {4, "\\265"}, {4, "\\266"}, {4, "\\267"},
+ {4, "\\270"}, {4, "\\271"}, {4, "\\272"}, {4, "\\273"},
+ {4, "\\274"}, {4, "\\275"}, {4, "\\276"}, {4, "\\277"},
+ {4, "\\300"}, {4, "\\301"}, {4, "\\302"}, {4, "\\303"},
+ {4, "\\304"}, {4, "\\305"}, {4, "\\306"}, {4, "\\307"},
+ {4, "\\310"}, {4, "\\311"}, {4, "\\312"}, {4, "\\313"},
+ {4, "\\314"}, {4, "\\315"}, {4, "\\316"}, {4, "\\317"},
+ {4, "\\320"}, {4, "\\321"}, {4, "\\322"}, {4, "\\323"},
+ {4, "\\324"}, {4, "\\325"}, {4, "\\326"}, {4, "\\327"},
+ {4, "\\330"}, {4, "\\331"}, {4, "\\332"}, {4, "\\333"},
+ {4, "\\334"}, {4, "\\335"}, {4, "\\336"}, {4, "\\337"},
+ {4, "\\340"}, {4, "\\341"}, {4, "\\342"}, {4, "\\343"},
+ {4, "\\344"}, {4, "\\345"}, {4, "\\346"}, {4, "\\347"},
+ {4, "\\350"}, {4, "\\351"}, {4, "\\352"}, {4, "\\353"},
+ {4, "\\354"}, {4, "\\355"}, {4, "\\356"}, {4, "\\357"},
+ {4, "\\360"}, {4, "\\361"}, {4, "\\362"}, {4, "\\363"},
+ {4, "\\364"}, {4, "\\365"}, {4, "\\366"}, {4, "\\367"},
+ {4, "\\370"}, {4, "\\371"}, {4, "\\372"}, {4, "\\373"},
+ {4, "\\374"}, {4, "\\375"}, {4, "\\376"}, {4, "\\377"}
+};
+
+#define FONTABSIZE 0x27
+
+struct strtab fontname[FONTABSIZE] = {
+ {19, "LucidaSansUnicode00", 0},
+ {19, "LucidaSansUnicode01", 0},
+ {19, "LucidaSansUnicode02", 0},
+ {19, "LucidaSansUnicode03", 0},
+ {19, "LucidaSansUnicode04", 0},
+ {19, "LucidaSansUnicode05", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {0, "", 0},
+ {19, "LucidaSansUnicode20", 0},
+ {19, "LucidaSansUnicode21", 0},
+ {19, "LucidaSansUnicode22", 0},
+ {0, "", 0},
+ {19, "LucidaSansUnicode24", 0},
+ {19, "LucidaSansUnicode25", 0},
+ {7, "Courier", 0}
+};
+
+/* This was taken from postprint */
+
+int
+cat(char *filename) {
+ Biobuf *bfile, *Bfile;
+ int n;
+ static char buf[Bsize];
+
+ bstdin = Bopen(filename, 0);
+ if (bstdin == 0) {
+ return(1);
+ }
+ Bstdin = bstdin;
+ if ((bfile = Bopen(filename, OREAD)) == 0) {
+ return(1);
+ }
+ Bfile = bfile;
+ while ((n=Bread(Bfile, buf, Bsize)) > 0) {
+ if (Bwrite(Bstdout, buf, n) != n) {
+ return(1);
+ }
+ }
+ if (n != 0) {
+ return(1);
+ }
+ return(0);
+}
+
+void
+prologues(void) {
+ char *ts;
+ int tabstop;
+
+ Bprint(Bstdout, "%s", CONFORMING);
+ Bprint(Bstdout, "%s %s\n", VERSION, PROGRAMVERSION);
+ Bprint(Bstdout, "%s %s\n", DOCUMENTFONTS, ATEND);
+ Bprint(Bstdout, "%s %s\n", PAGES, ATEND);
+ Bprint(Bstdout, "%s", ENDCOMMENTS);
+
+ if (cat(POSTPRINT)) {
+ Bprint(Bstderr, "can't read %s", POSTPRINT);
+ exits("prologue");
+ }
+
+ if (DOROUND)
+ cat(ROUNDPAGE);
+
+ tabstop = 0;
+ ts = getenv("tabstop");
+ if(ts != nil)
+ tabstop = strtol(ts, nil, 0);
+ if(tabstop == 0)
+ tabstop = 8;
+ Bprint(Bstdout, "/f {findfont pointsize scalefont setfont} bind def\n");
+ Bprint(Bstdout, "/tabwidth /Courier f (");
+ while(tabstop--)
+ Bputc(Bstdout, 'n');
+ Bprint(Bstdout, ") stringwidth pop def\n");
+ Bprint(Bstdout, "/tab {tabwidth 0 ne {currentpoint 3 1 roll exch tabwidth mul add tabwidth\n");
+ Bprint(Bstdout, "\tdiv truncate tabwidth mul exch moveto} if} bind def\n");
+ Bprint(Bstdout, "/spacewidth /%s f ( ) stringwidth pop def\n", fontname[0].str);
+ Bprint(Bstdout, "/sp {spacewidth mul 0 rmoveto} bind def\n");
+ Bprint(Bstdout, "%s", ENDPROLOG);
+ Bprint(Bstdout, "%s", BEGINSETUP);
+ Bprint(Bstdout, "mark\n");
+
+ if (formsperpage > 1) {
+ Bprint(Bstdout, "%s %d\n", FORMSPERPAGE, formsperpage);
+ Bprint(Bstdout, "/formsperpage %d def\n", formsperpage);
+ }
+ if (aspectratio != 1) Bprint(Bstdout, "/aspectratio %g def\n", aspectratio);
+ if (copies != 1) Bprint(Bstdout, "/#copies %d store\n", copies);
+ if (landscape) Bprint(Bstdout, "/landscape true def\n");
+ if (magnification != 1) Bprint(Bstdout, "/magnification %s def\n", magnification);
+ if (pointsize != 10) Bprint(Bstdout, "/pointsize %d def\n", pointsize);
+ if (xoffset != .25) Bprint(Bstdout, "/xoffset %g def\n", xoffset);
+ if (yoffset != .25) Bprint(Bstdout, "/yoffset %g def\n", yoffset);
+ cat(unsharp("#9/postscript/prologues/Latin1.enc"));
+ if (passthrough != 0) Bprint(Bstdout, "%s\n", passthrough);
+ Bprint(Bstdout, "setup\n");
+ if (formsperpage > 1) {
+ cat(FORMFILE);
+ Bprint(Bstdout, "%d setupforms \n", formsperpage);
+ }
+ if (cat(UNKNOWNCHAR))
+ Bprint(Bstderr, "cannot open %s\n", UNKNOWNCHAR);
+ Bprint(Bstdout, "%s", ENDSETUP);
+}
+
+int
+pageon(void) {
+ if (pplist == 0 && page_no != 0) return(1); /* no page list, print all pages */
+ if (page_no/8 < pplistmaxsize && (pplist[page_no/8] & 1<<(page_no%8)))
+ return(1);
+ else
+ return(0);
+}
+
+void
+startpage(void) {
+ ++char_no;
+ ++line_no;
+ ++page_no;
+ if (pageon()) {
+ ++pages_printed;
+ Bprint(Bstdout, "%s %d %d\n", PAGE, page_no, pages_printed);
+ Bprint(Bstdout, "/saveobj save def\n");
+ Bprint(Bstdout, "mark\n");
+ Bprint(Bstdout, "%d pagesetup\n", pages_printed);
+ }
+}
+
+void
+endpage(void) {
+ line_no = 0;
+ char_no = 0;
+ if (pageon()) {
+ Bprint(Bstdout, "cleartomark\n");
+ Bprint(Bstdout, "showpage\n");
+ Bprint(Bstdout, "saveobj restore\n");
+ Bprint(Bstdout, "%s %d %d\n", ENDPAGE, page_no, pages_printed);
+ }
+}
+
+void
+startstring(void) {
+ if (!in_string) {
+ if (pageon()) Bprint(Bstdout, "(");
+ in_string = 1;
+ }
+}
+
+void
+endstring(void) {
+ if (in_string) {
+ if (pageon()) Bprint(Bstdout, ") show ");
+ in_string = 0;
+ }
+}
+
+void
+prspace(void) {
+ if (spaces) {
+ endstring();
+ if (pageon()) Bprint(Bstdout, "%d sp ", spaces);
+ spaces = 0;
+ }
+}
+
+void
+prtab(void) {
+ if (tabs) {
+ endstring();
+ if (pageon()) Bprint(Bstdout, "%d tab ", tabs);
+ tabs = 0;
+ }
+}
+
+void
+txt2post(void) {
+ int lastfont = -1;
+ int lastchar = -1;
+ int thisfont, thischar;
+ long r;
+
+ in_string = 0;
+ char_no = 0;
+ line_no = 0;
+ page_no = 0;
+ spaces = 0;
+ fontname[0].used++;
+ while ((r=Bgetrune(Bstdin)) >= 0) {
+ thischar = r & 0xff;
+ thisfont = (r>>8) & 0xff;
+
+ if (line_no == 0 && char_no == 0)
+ startpage();
+
+ if (line_no == 1 && char_no == 1) {
+ if (pageon()) Bprint(Bstdout, " /%s f\n", fontname[thisfont].str);
+ lastfont = thisfont;
+ }
+
+ switch (r) {
+ case ' ':
+ prtab();
+ if (lastfont > 0) {
+ spaces++;
+ continue;
+ }
+ break;
+ case '\n':
+ case '\f':
+ startstring();
+ if (pageon()) Bprint(Bstdout, ")l\n");
+ char_no = 1;
+ in_string = 0;
+ spaces = 0;
+ tabs = 0;
+ if (++line_no > linesperpage || r == '\f') {
+ endpage();
+ }
+ lastchar = -1;
+ continue;
+ case '\t':
+ prspace();
+ tabs++;
+ char_no++;
+ lastchar = -1;
+ continue;
+ case '\b':
+ /* just toss out backspaces for now */
+ if (lastchar != -1) {
+ endstring();
+ if (pageon()) Bprint(Bstdout, "(%s) stringwidth pop neg 0 rmoveto ", charcode[lastchar].str);
+ }
+ char_no++;
+ lastchar = -1;
+ continue;
+ }
+
+ /* do something if font is out of table range */
+ if (thisfont>=FONTABSIZE || fontname[thisfont].size == 0) {
+ prspace();
+ prtab();
+ endstring();
+ Bprint(Bstdout, "pw ");
+ char_no++;
+ lastchar = -1;
+ continue;
+ }
+
+ if (thisfont != lastfont) {
+ endstring();
+ if (pageon()) {
+ Bprint(Bstdout, "/%s f\n", fontname[thisfont].str);
+ }
+ fontname[thisfont].used++;
+ }
+ prspace();
+ prtab();
+ startstring();
+ if (pageon()) Bprint(Bstdout, "%s", charcode[thischar].str);
+/* if (pageon()) Bprint(Bstdout, "%2.2x", thischar); /* try hex strings*/
+ char_no++;
+ lastchar = thischar;
+ lastfont = thisfont;
+ }
+ if (line_no != 0 || char_no != 0) {
+ if (char_no != 1) {
+ Bprint(Bstderr, "premature EOF: newline appended\n");
+ startstring();
+ if (pageon()) Bprint(Bstdout, ")l\n");
+ }
+ endpage();
+ }
+}
+
+void
+pagelist(char *list) {
+ char c;
+ int n, m;
+ int state, start, end;
+
+ if (list == 0) return;
+ state = 1;
+ while ((c=*list) != '\0') {
+ n = 0;
+ while (isdigit(c)) {
+ n = n * 10 + c - '0';
+ c = *++list;
+ }
+ switch (state) {
+ case 1:
+ start = n;
+ case 2:
+ if (n/8+1 > pplistmaxsize) {
+ pplistmaxsize = n/8+1;
+ if ((pplist = realloc(pplist, n/8+1)) == 0) {
+ Bprint(Bstderr, "cannot allocate memory for page list\n");
+ exits("malloc");
+ }
+ }
+ for (m=start; m<=n; m++)
+ pplist[m/8] |= 1<<(m%8);
+ break;
+ }
+ switch (c) {
+ case '-':
+ state = 2;
+ list++;
+ break;
+ case ',':
+ state = 1;
+ list++;
+ break;
+ case '\0':
+ break;
+ }
+ }
+}
+
+void
+finish(void) {
+ int i;
+
+ Bprint(Bstdout, "%s", TRAILER);
+ Bprint(Bstdout, "done\n");
+ Bprint(Bstdout, "%s", DOCUMENTFONTS);
+
+ for (i=0; i<FONTABSIZE; i++)
+ if (fontname[i].used)
+ Bprint(Bstdout, " %s", fontname[i].str);
+ Bprint(Bstdout, "\n");
+
+ Bprint(Bstdout, "%s %d\n", PAGES, pages_printed);
+
+}
+
+main(int argc, char *argv[]) {
+ int i;
+ char *t;
+ Biobuf *input;
+
+ if ((bstderr = (Biobuf *)malloc(sizeof(Biobuf))) < (Biobuf *)0)
+ exits("malloc");
+ if (Binit(bstderr, 2, OWRITE) == Beof)
+ exits("Binit");
+ Bstderr = bstderr;
+
+ if ((bstdout = (Biobuf *)malloc(sizeof(Biobuf))) < (Biobuf *)0)
+ exits("malloc");
+ if (Binit(bstdout, 1, OWRITE) == Beof)
+ exits("Binit");
+ Bstdout = bstdout;
+
+ ARGBEGIN{
+ case 'a': /* aspect ratio */
+ aspectratio = atof(ARGF());
+ break;
+ case 'c': /* copies */
+ copies = atoi(ARGF());
+ break;
+ case 'f': /* primary font, for now */
+ t = ARGF();
+ fontname[0].str = malloc(strlen(t)+1);
+ strcpy(fontname[0].str, t);
+ break;
+ case 'l': /* lines per page */
+ linesperpage = atoi(ARGF());
+ break;
+ case 'm': /* magnification */
+ magnification = atof(ARGF());
+ break;
+ case 'n': /* forms per page */
+ formsperpage = atoi(ARGF());
+ break;
+ case 'o': /* output page list */
+ pagelist(ARGF());
+ break;
+ case 'p': /* landscape or portrait mode */
+ if ( ARGF()[0] == 'l' )
+ landscape = 1;
+ else
+ landscape = 0;
+ break;
+ case 's': /* point size */
+ pointsize = atoi(ARGF());
+ break;
+ case 'x': /* shift things horizontally */
+ xoffset = atof(ARGF());
+ break;
+
+ case 'y': /* and vertically on the page */
+ yoffset = atof(ARGF());
+ break;
+ case 'P': /* PostScript pass through */
+ t = ARGF();
+ i = strlen(t) + 1;
+ passthrough = malloc(i);
+ if (passthrough == 0) {
+ Bprint(Bstderr, "cannot allocate memory for argument string\n");
+ exits("malloc");
+ }
+ strncpy(passthrough, t, i);
+ break;
+ default: /* don't know what to do for ch */
+ Bprint(Bstderr, "unknown option %C\n", ARGC());
+ break;
+ }ARGEND;
+ prologues();
+ if (argc <= 0) {
+ if ((bstdin = (Biobuf *)malloc(sizeof(Biobuf))) < (Biobuf *)0)
+ exits("malloc");
+ if (Binit(bstdin, 0, OREAD) == Beof) {
+ fprint(2, "cannot Binit stdin\n");
+ exits("Binit");
+ }
+ Bstdin = bstdin;
+ txt2post();
+ }
+ for (i=0; i<argc; i++) {
+ bstdin = Bopen(argv[i], 0);
+ if (bstdin == 0) {
+ fprint(2, "cannot open file %s\n", argv[i]);
+ continue;
+ }
+ Bstdin = bstdin;
+ txt2post();
+ }
+ finish();
+ exits("");
+}
