From 5324dcc64cad1457c3978e9850f63a6b0f8dffeb Mon Sep 17 00:00:00 2001
From: Giuseppe Bilotta <giuseppe.bilotta@gmail.com>
Date: Sun, 16 Mar 2008 10:22:38 +0100
Subject: [PATCH] Unit tests for CWEB

---
 test/expected_dir/cweb.w/c/blanks             |   1 +
 test/expected_dir/cweb.w/c/code               | 177 ++++++++
 test/expected_dir/cweb.w/documentation/blanks |   1 +
 .../expected_dir/cweb.w/documentation/comment | 197 +++++++++
 test/src_dir/cweb.w                           | 415 ++++++++++++++++++
 test/unit/cweb_test.rb                        |   7 +
 6 files changed, 798 insertions(+)
 create mode 100644 test/expected_dir/cweb.w/c/blanks
 create mode 100644 test/expected_dir/cweb.w/c/code
 create mode 100644 test/expected_dir/cweb.w/documentation/blanks
 create mode 100644 test/expected_dir/cweb.w/documentation/comment
 create mode 100644 test/src_dir/cweb.w
 create mode 100644 test/unit/cweb_test.rb

diff --git a/test/expected_dir/cweb.w/c/blanks b/test/expected_dir/cweb.w/c/blanks
new file mode 100644
index 0000000..19c7bdb
--- /dev/null
+++ b/test/expected_dir/cweb.w/c/blanks
@@ -0,0 +1 @@
+16
\ No newline at end of file
diff --git a/test/expected_dir/cweb.w/c/code b/test/expected_dir/cweb.w/c/code
new file mode 100644
index 0000000..8004ca8
--- /dev/null
+++ b/test/expected_dir/cweb.w/c/code
@@ -0,0 +1,177 @@
+@d banner "This is MetaPost, Version 1.002" /* printed when \MP\ starts */
+@d metapost_version "1.002"
+@d mplib_version "0.20"
+@d version_string " (Cweb version 0.20)"
+@d true 1
+@d false 0
+typedef struct MP_instance * MP;
+typedef struct MP_options {
+} MP_options;
+#include <setjmp.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdarg.h>
+#include <assert.h>
+#include <unistd.h> /* for access() */
+#include <time.h> /* for struct tm \& co */
+#include "mplib.h"
+#include "mpmp.h" /* internal header */
+#include "mppsout.h" /* internal header */
+@h
+#if !defined(__GNUC__) || (__GNUC__ < 2)
+# define __attribute__(x)
+#endif /* !defined(__GNUC__) || (__GNUC__ < 2) */
+void  __attribute__((noinline))
+mp_do_initialize ( MP mp) {
+}
+int mp_initialize (MP mp) { /* this procedure gets things started properly */
+mp->history=mp_fatal_error_stop; /* in case we quit during initialization */
+t_open_out; /* open the terminal for output */
+if ( mp->bad>0 ) {
+char ss[256];
+snprintf(ss,256,"Ouch---my internal constants have been clobbered!\n"
+"---case %i",(int)mp->bad);
+do_fprintf(mp->err_out,(char *)ss);
+return mp->history;
+}
+mp_do_initialize(mp); /* erase preloaded mem */
+if (mp->ini_version) {
+}
+mp_set_job_id(mp);
+mp_init_map_file(mp, mp->troff_mode);
+mp->history=mp_spotless; /* ready to go! */
+if (mp->troff_mode) {
+mp->internal[mp_gtroffmode]=unity; 
+mp->internal[mp_prologues]=unity; 
+}
+if ( mp->start_sym>0 ) { /* insert the `\&{everyjob}' symbol */
+mp->cur_sym=mp->start_sym; mp_back_input(mp);
+}
+return mp->history;
+}
+for (i=first_text_char;i<=last_text_char;i++) { 
+xord(chr(i))=0177;
+}
+for (i=0200;i<=0377;i++) { xord(xchr(i))=i;}
+for (i=0;i<=0176;i++) { xord(xchr(i))=i;}
+@d loc mp->cur_input.loc_field /* location of first unread character in |buffer| */
+boolean mp_init_terminal (MP mp) { /* gets the terminal input started */
+t_open_in; 
+if (mp->last!=0) {
+loc = mp->first = 0;
+return true;
+}
+while (1) { 
+wake_up_terminal; do_fprintf(mp->term_out,"**"); update_terminal;
+if ( ! mp_input_ln(mp, mp->term_in ) ) { /* this shouldn't happen */
+do_fprintf(mp->term_out,"\n! End of file on the terminal... why?");
+return false;
+}
+loc=mp->first;
+while ( (loc<(int)mp->last)&&(mp->buffer[loc]==' ') ) 
+incr(loc);
+if ( loc<(int)mp->last ) { 
+return true; /* return unless the line was all blank */
+};
+do_fprintf(mp->term_out,"Please type the name of your input file.\n");
+}
+}
+boolean mp_init_terminal (MP mp) ;
+mp_primitive(mp, "tracingtitles",internal_quantity,mp_tracing_titles);
+mp_primitive(mp, "tracingequations",internal_quantity,mp_tracing_equations);
+mp_primitive(mp, "tracingcapsules",internal_quantity,mp_tracing_capsules);
+mp_primitive(mp, "tracingchoices",internal_quantity,mp_tracing_choices);
+mp_primitive(mp, "tracingspecs",internal_quantity,mp_tracing_specs);
+mp_primitive(mp, "tracingcommands",internal_quantity,mp_tracing_commands);
+mp_primitive(mp, "tracingrestores",internal_quantity,mp_tracing_restores);
+mp_primitive(mp, "tracingmacros",internal_quantity,mp_tracing_macros);
+mp_primitive(mp, "tracingoutput",internal_quantity,mp_tracing_output);
+mp_primitive(mp, "tracingstats",internal_quantity,mp_tracing_stats);
+mp_primitive(mp, "tracinglostchars",internal_quantity,mp_tracing_lost_chars);
+mp_primitive(mp, "tracingonline",internal_quantity,mp_tracing_online);
+mp_primitive(mp, "year",internal_quantity,mp_year);
+mp_primitive(mp, "month",internal_quantity,mp_month);
+mp_primitive(mp, "day",internal_quantity,mp_day);
+mp_primitive(mp, "time",internal_quantity,mp_time);
+mp_primitive(mp, "charcode",internal_quantity,mp_char_code);
+mp_primitive(mp, "charext",internal_quantity,mp_char_ext);
+mp_primitive(mp, "charwd",internal_quantity,mp_char_wd);
+mp_primitive(mp, "charht",internal_quantity,mp_char_ht);
+mp_primitive(mp, "chardp",internal_quantity,mp_char_dp);
+mp_primitive(mp, "charic",internal_quantity,mp_char_ic);
+mp_primitive(mp, "designsize",internal_quantity,mp_design_size);
+mp_primitive(mp, "pausing",internal_quantity,mp_pausing);
+mp_primitive(mp, "showstopping",internal_quantity,mp_showstopping);
+mp_primitive(mp, "fontmaking",internal_quantity,mp_fontmaking);
+mp_primitive(mp, "linejoin",internal_quantity,mp_linejoin);
+mp_primitive(mp, "linecap",internal_quantity,mp_linecap);
+mp_primitive(mp, "miterlimit",internal_quantity,mp_miterlimit);
+mp_primitive(mp, "warningcheck",internal_quantity,mp_warning_check);
+mp_primitive(mp, "boundarychar",internal_quantity,mp_boundary_char);
+mp_primitive(mp, "prologues",internal_quantity,mp_prologues);
+mp_primitive(mp, "truecorners",internal_quantity,mp_true_corners);
+mp_primitive(mp, "mpprocset",internal_quantity,mp_procset);
+mp_primitive(mp, "troffmode",internal_quantity,mp_gtroffmode);
+mp_primitive(mp, "defaultcolormodel",internal_quantity,mp_default_color_model);
+mp_primitive(mp, "restoreclipcolor",internal_quantity,mp_restore_clip_color);
+void mp_debug_help (MP mp) { /* routine to display various things */
+integer k;
+int l,m,n;
+char *aline;
+size_t len;
+while (1) { 
+wake_up_terminal;
+mp_print_nl(mp, "debug # (-1 to exit):"); update_terminal;
+m = 0;
+aline = (mp->read_ascii_file)(mp->term_in, &len);
+if (len) { sscanf(aline,"%i",&m); xfree(aline); }
+if ( m<=0 )
+return;
+n = 0 ;
+aline = (mp->read_ascii_file)(mp->term_in, &len);
+if (len) { sscanf(aline,"%i",&n); xfree(aline); }
+switch (m) {
+default: mp_print(mp, "?"); break;
+}
+}
+}
+case 1: mp_print_word(mp, mp->mem[n]); /* display |mem[n]| in all forms */
+break;
+case 2: mp_print_int(mp, info(n));
+break;
+case 3: mp_print_int(mp, link(n));
+break;
+case 4: mp_print_int(mp, eq_type(n)); mp_print_char(mp, ':'); mp_print_int(mp, equiv(n));
+break;
+case 5: mp_print_variable_name(mp, n);
+break;
+case 6: mp_print_int(mp, mp->internal[n]);
+break;
+case 7: mp_do_show_dependencies(mp);
+break;
+case 9: mp_show_token_list(mp, n,null,100000,0);
+break;
+case 10: mp_print_str(mp, n);
+break;
+case 11: mp_check_mem(mp, n>0); /* check wellformedness; print new busy locations if |n>0| */
+break;
+case 12: mp_search_mem(mp, n); /* look for pointers to |n| */
+break;
+case 13: 
+l = 0;  
+aline = (mp->read_ascii_file)(mp->term_in, &len);
+if (len) { sscanf(aline,"%i",&l); xfree(aline); }
+mp_print_cmd_mod(mp, n,l); 
+break;
+case 14: for (k=0;k<=n;k++) mp_print_str(mp, mp->buffer[k]);
+break;
+case 15: mp->panicking=! mp->panicking;
+break;
+{ 
+if ( mp->filename_template!=0 ) delete_str_ref(mp->filename_template);
+if ( length(mp->cur_exp)==0 ) mp->filename_template=0;
+else { 
+mp->filename_template=mp->cur_exp; add_str_ref(mp->filename_template);
+}
+}
diff --git a/test/expected_dir/cweb.w/documentation/blanks b/test/expected_dir/cweb.w/documentation/blanks
new file mode 100644
index 0000000..410b14d
--- /dev/null
+++ b/test/expected_dir/cweb.w/documentation/blanks
@@ -0,0 +1 @@
+25
\ No newline at end of file
diff --git a/test/expected_dir/cweb.w/documentation/comment b/test/expected_dir/cweb.w/documentation/comment
new file mode 100644
index 0000000..0f00dc8
--- /dev/null
+++ b/test/expected_dir/cweb.w/documentation/comment
@@ -0,0 +1,197 @@
+% Sample CWEB file, excerpts from the libmp source code
+@* \[1] Introduction.
+A large piece of software like \MP\ has inherent complexity that cannot
+be reduced below a certain level of difficulty, although each individual
+part is fairly simple by itself. The \.{WEB} language is intended to make
+the algorithms as readable as possible, by reflecting the way the
+individual program pieces fit together and by providing the
+cross-references that connect different parts. Detailed comments about
+what is going on, and about why things were done in certain ways, have
+been liberally sprinkled throughout the program.  These comments explain
+features of the implementation, but they rarely attempt to explain the
+\MP\ language itself, since the reader is supposed to be familiar with
+{\sl The {\logos METAFONT\/}book} as well as the manual
+@.WEB@>
+@:METAFONTbook}{\sl The {\logos METAFONT\/}book@>
+{\sl A User's Manual for MetaPost}, Computing Science Technical Report 162,
+AT\AM T Bell Laboratories.
+@ The present implementation is a preliminary version, but the possibilities
+for new features are limited by the desire to remain as nearly compatible
+with \MF\ as possible.
+On the other hand, the \.{WEB} description can be extended without changing
+the core of the program, and it has been designed so that such
+extensions are not extremely difficult to make.
+The |banner| string defined here should be changed whenever \MP\
+undergoes any modifications, so that it will be clear which version of
+\MP\ might be the guilty party when a problem arises.
+@^extensions to \MP@>
+@^system dependencies@>
+@ The external library header for \MP\ is |mplib.h|. It contains a
+few typedefs and the header defintions for the externally used
+fuctions.
+The most important of the typedefs is the definition of the structure 
+|MP_options|, that acts as a small, configurable front-end to the fairly 
+large |MP_instance| structure.
+@(mplib.h@>=
+@<Exported types@>
+@<Option variables@>
+@<Exported function headers@>
+@ The internal header file is much longer: it not only lists the complete
+|MP_instance|, but also a lot of functions that have to be available to
+the \ps\ backend, that is defined in a separate \.{WEB} file. 
+The variables from |MP_options| are included inside the |MP_instance| 
+wholesale.
+@(mpmp.h@>=
+@<Internal library declarations@>
+@ @c 
+@<Declarations@>
+@<Basic printing procedures@>
+@<Error handling procedures@>
+@ The |__attribute__| pragma is gcc-only.
+@<Internal library ... @>=
+@ @c
+@<Local variables for initialization@>
+@<Set initial values of key variables@>
+@<Install and test the non-local jump buffer@>;
+@<Check the ``constant'' values...@>;
+@.Ouch...clobbered@>
+@<Run inimpost commands@>;
+@<Initialize the output routines@>;
+@<Get the first line of input and prepare to start@>;
+@ The following system-independent code makes the |xord| array contain a
+suitable inverse to the information in |xchr|. Note that if |xchr[i]=xchr[j]|
+where |i<j<0177|, the value of |xord[xchr[i]]| will turn out to be
+|j| or more; hence, standard ASCII code numbers will be used instead of
+codes below 040 in case there is a coincidence.
+@<Set initial ...@>=
+@* \[3] Input and output.
+The bane of portability is the fact that different operating systems treat
+input and output quite differently, perhaps because computer scientists
+have not given sufficient attention to this problem. People have felt somehow
+that input and output are not part of ``real'' programming. Well, it is true
+that some kinds of programming are more fun than others. With existing
+input/output conventions being so diverse and so messy, the only sources of
+joy in such parts of the code are the rare occasions when one can find a
+way to make the program a little less bad than it might have been. We have
+two choices, either to attack I/O now and get it over with, or to postpone
+I/O until near the end. Neither prospect is very attractive, so let's
+get it over with.
+Different systems have different ways to get started. But regardless of
+what conventions are adopted, the routine that initializes the terminal
+should satisfy the following specifications:
+\yskip\textindent{1)}It should open file |term_in| for input from the
+terminal. (The file |term_out| will already be open for output to the
+terminal.)
+\textindent{2)}If the user has given a command line, this line should be
+considered the first line of terminal input. Otherwise the
+user should be prompted with `\.{**}', and the first line of input
+should be whatever is typed in response.
+\textindent{3)}The first line of input, which might or might not be a
+command line, should appear in locations |first| to |last-1| of the
+|buffer| array.
+\textindent{4)}The global variable |loc| should be set so that the
+character to be read next by \MP\ is in |buffer[loc]|. This
+character should not be blank, and we should have |loc<last|.
+\yskip\noindent(It may be necessary to prompt the user several times
+before a non-blank line comes in. The prompt is `\.{**}' instead of the
+later `\.*' because the meaning is slightly different: `\.{input}' need
+not be typed immediately after~`\.{**}'.)
+@ The following program does the required initialization
+without retrieving a possible command line.
+It should be clear how to modify this routine to deal with command lines,
+if the system permits them.
+@^system dependencies@>
+@c 
+@.**@>
+@.End of file on the terminal@>
+@ @<Declarations@>=
+@ The symbolic names for internal quantities are put into \MP's hash table
+by using a routine called |primitive|, which will be defined later. Let us
+enter them now, so that we don't have to list all those names again
+anywhere else.
+@<Put each of \MP's primitives into the hash table@>=
+@:tracingtitles_}{\&{tracingtitles} primitive@>
+@:mp_tracing_equations_}{\&{tracingequations} primitive@>
+@:mp_tracing_capsules_}{\&{tracingcapsules} primitive@>
+@:mp_tracing_choices_}{\&{tracingchoices} primitive@>
+@:mp_tracing_specs_}{\&{tracingspecs} primitive@>
+@:mp_tracing_commands_}{\&{tracingcommands} primitive@>
+@:mp_tracing_restores_}{\&{tracingrestores} primitive@>
+@:mp_tracing_macros_}{\&{tracingmacros} primitive@>
+@:mp_tracing_output_}{\&{tracingoutput} primitive@>
+@:mp_tracing_stats_}{\&{tracingstats} primitive@>
+@:mp_tracing_lost_chars_}{\&{tracinglostchars} primitive@>
+@:mp_tracing_online_}{\&{tracingonline} primitive@>
+@:mp_year_}{\&{year} primitive@>
+@:mp_month_}{\&{month} primitive@>
+@:mp_day_}{\&{day} primitive@>
+@:time_}{\&{time} primitive@>
+@:mp_char_code_}{\&{charcode} primitive@>
+@:mp_char_ext_}{\&{charext} primitive@>
+@:mp_char_wd_}{\&{charwd} primitive@>
+@:mp_char_ht_}{\&{charht} primitive@>
+@:mp_char_dp_}{\&{chardp} primitive@>
+@:mp_char_ic_}{\&{charic} primitive@>
+@:mp_design_size_}{\&{designsize} primitive@>
+@:mp_pausing_}{\&{pausing} primitive@>
+@:mp_showstopping_}{\&{showstopping} primitive@>
+@:mp_fontmaking_}{\&{fontmaking} primitive@>
+@:mp_linejoin_}{\&{linejoin} primitive@>
+@:mp_linecap_}{\&{linecap} primitive@>
+@:mp_miterlimit_}{\&{miterlimit} primitive@>
+@:mp_warning_check_}{\&{warningcheck} primitive@>
+@:mp_boundary_char_}{\&{boundarychar} primitive@>
+@:mp_prologues_}{\&{prologues} primitive@>
+@:mp_true_corners_}{\&{truecorners} primitive@>
+@:mp_procset_}{\&{mpprocset} primitive@>
+@:troffmode_}{\&{troffmode} primitive@>
+@:mp_default_color_model_}{\&{defaultcolormodel} primitive@>
+@:mp_restore_clip_color_}{\&{restoreclipcolor} primitive@>
+@* \[47] Debugging.
+Once \MP\ is working, you should be able to diagnose most errors with
+the \.{show} commands and other diagnostic features. But for the initial
+stages of debugging, and for the revelation of really deep mysteries, you
+can compile \MP\ with a few more aids. An additional routine called |debug_help|
+will also come into play when you type `\.D' after an error message;
+|debug_help| also occurs just before a fatal error causes \MP\ to succumb.
+@^debugging@>
+@^system dependencies@>
+The interface to |debug_help| is primitive, but it is good enough when used
+with a debugger that allows you to set breakpoints and to read
+variables and change their values. After getting the prompt `\.{debug \#}', you
+type either a negative number (this exits |debug_help|), or zero (this
+goes to a location where you can set a breakpoint, thereby entering into
+dialog with the debugger), or a positive number |m| followed by
+an argument |n|. The meaning of |m| and |n| will be clear from the
+program below. (If |m=13|, there is an additional argument, |l|.)
+@.debug \#@>
+@<Last-minute...@>=
+@.debug \#@>
+@<Numbered cases for |debug_help|@>;
+@ @<Numbered cases...@>=
+@ Saving the filename template
+@<Save the filename template@>=
+@* \[48] System-dependent changes.
+This section should be replaced, if necessary, by any special
+modification of the program
+that are necessary to make \MP\ work at a particular installation.
+It is usually best to design your change file so that all changes to
+previous sections preserve the section numbering; then everybody's version
+will be consistent with the published program. More extensive changes,
+which introduce new sections, can be inserted here; then only the index
+itself will get a new section number.
+@^system dependencies@>
+@* \[49] Index.
+Here is where you can find all uses of each identifier in the program,
+with underlined entries pointing to where the identifier was defined.
+If the identifier is only one letter long, however, you get to see only
+the underlined entries. {\sl All references are to section numbers instead of
+page numbers.}
+This index also lists error messages and other aspects of the program
+that you might want to look up some day. For example, the entry
+for ``system dependencies'' lists all sections that should receive
+special attention from people who are installing \MP\ in a new
+operating environment. A list of various things that can't happen appears
+under ``this can't happen''.
+Approximately 25 sections are listed under ``inner loop''; these account
+for more than 60\pct! of \MP's running time, exclusive of input and output.
diff --git a/test/src_dir/cweb.w b/test/src_dir/cweb.w
new file mode 100644
index 0000000..28349b1
--- /dev/null
+++ b/test/src_dir/cweb.w
@@ -0,0 +1,415 @@
+% Sample CWEB file, excerpts from the libmp source code
+
+@* \[1] Introduction.
+
+A large piece of software like \MP\ has inherent complexity that cannot
+be reduced below a certain level of difficulty, although each individual
+part is fairly simple by itself. The \.{WEB} language is intended to make
+the algorithms as readable as possible, by reflecting the way the
+individual program pieces fit together and by providing the
+cross-references that connect different parts. Detailed comments about
+what is going on, and about why things were done in certain ways, have
+been liberally sprinkled throughout the program.  These comments explain
+features of the implementation, but they rarely attempt to explain the
+\MP\ language itself, since the reader is supposed to be familiar with
+{\sl The {\logos METAFONT\/}book} as well as the manual
+@.WEB@>
+@:METAFONTbook}{\sl The {\logos METAFONT\/}book@>
+{\sl A User's Manual for MetaPost}, Computing Science Technical Report 162,
+AT\AM T Bell Laboratories.
+
+@ The present implementation is a preliminary version, but the possibilities
+for new features are limited by the desire to remain as nearly compatible
+with \MF\ as possible.
+
+On the other hand, the \.{WEB} description can be extended without changing
+the core of the program, and it has been designed so that such
+extensions are not extremely difficult to make.
+The |banner| string defined here should be changed whenever \MP\
+undergoes any modifications, so that it will be clear which version of
+\MP\ might be the guilty party when a problem arises.
+@^extensions to \MP@>
+@^system dependencies@>
+
+@d banner "This is MetaPost, Version 1.002" /* printed when \MP\ starts */
+@d metapost_version "1.002"
+@d mplib_version "0.20"
+@d version_string " (Cweb version 0.20)"
+
+@d true 1
+@d false 0
+
+@ The external library header for \MP\ is |mplib.h|. It contains a
+few typedefs and the header defintions for the externally used
+fuctions.
+
+The most important of the typedefs is the definition of the structure 
+|MP_options|, that acts as a small, configurable front-end to the fairly 
+large |MP_instance| structure.
+ 
+@(mplib.h@>=
+typedef struct MP_instance * MP;
+@<Exported types@>
+typedef struct MP_options {
+  @<Option variables@>
+} MP_options;
+@<Exported function headers@>
+
+@ The internal header file is much longer: it not only lists the complete
+|MP_instance|, but also a lot of functions that have to be available to
+the \ps\ backend, that is defined in a separate \.{WEB} file. 
+
+The variables from |MP_options| are included inside the |MP_instance| 
+wholesale.
+
+@(mpmp.h@>=
+#include <setjmp.h>
+@<Internal library declarations@>
+
+@ @c 
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdarg.h>
+#include <assert.h>
+#include <unistd.h> /* for access() */
+#include <time.h> /* for struct tm \& co */
+#include "mplib.h"
+#include "mpmp.h" /* internal header */
+#include "mppsout.h" /* internal header */
+@h
+@<Declarations@>
+@<Basic printing procedures@>
+@<Error handling procedures@>
+
+@ The |__attribute__| pragma is gcc-only.
+
+@<Internal library ... @>=
+#if !defined(__GNUC__) || (__GNUC__ < 2)
+# define __attribute__(x)
+#endif /* !defined(__GNUC__) || (__GNUC__ < 2) */
+
+@ @c
+void  __attribute__((noinline))
+mp_do_initialize ( MP mp) {
+  @<Local variables for initialization@>
+  @<Set initial values of key variables@>
+}
+int mp_initialize (MP mp) { /* this procedure gets things started properly */
+  mp->history=mp_fatal_error_stop; /* in case we quit during initialization */
+  @<Install and test the non-local jump buffer@>;
+  t_open_out; /* open the terminal for output */
+  @<Check the ``constant'' values...@>;
+  if ( mp->bad>0 ) {
+	char ss[256];
+    snprintf(ss,256,"Ouch---my internal constants have been clobbered!\n"
+                   "---case %i",(int)mp->bad);
+    do_fprintf(mp->err_out,(char *)ss);
+@.Ouch...clobbered@>
+    return mp->history;
+  }
+  mp_do_initialize(mp); /* erase preloaded mem */
+  if (mp->ini_version) {
+    @<Run inimpost commands@>;
+  }
+  @<Initialize the output routines@>;
+  @<Get the first line of input and prepare to start@>;
+  mp_set_job_id(mp);
+  mp_init_map_file(mp, mp->troff_mode);
+  mp->history=mp_spotless; /* ready to go! */
+  if (mp->troff_mode) {
+    mp->internal[mp_gtroffmode]=unity; 
+    mp->internal[mp_prologues]=unity; 
+  }
+  if ( mp->start_sym>0 ) { /* insert the `\&{everyjob}' symbol */
+    mp->cur_sym=mp->start_sym; mp_back_input(mp);
+  }
+  return mp->history;
+}
+
+@ The following system-independent code makes the |xord| array contain a
+suitable inverse to the information in |xchr|. Note that if |xchr[i]=xchr[j]|
+where |i<j<0177|, the value of |xord[xchr[i]]| will turn out to be
+|j| or more; hence, standard ASCII code numbers will be used instead of
+codes below 040 in case there is a coincidence.
+
+@<Set initial ...@>=
+for (i=first_text_char;i<=last_text_char;i++) { 
+   xord(chr(i))=0177;
+}
+for (i=0200;i<=0377;i++) { xord(xchr(i))=i;}
+for (i=0;i<=0176;i++) { xord(xchr(i))=i;}
+
+@* \[3] Input and output.
+The bane of portability is the fact that different operating systems treat
+input and output quite differently, perhaps because computer scientists
+have not given sufficient attention to this problem. People have felt somehow
+that input and output are not part of ``real'' programming. Well, it is true
+that some kinds of programming are more fun than others. With existing
+input/output conventions being so diverse and so messy, the only sources of
+joy in such parts of the code are the rare occasions when one can find a
+way to make the program a little less bad than it might have been. We have
+two choices, either to attack I/O now and get it over with, or to postpone
+I/O until near the end. Neither prospect is very attractive, so let's
+get it over with.
+
+Different systems have different ways to get started. But regardless of
+what conventions are adopted, the routine that initializes the terminal
+should satisfy the following specifications:
+
+\yskip\textindent{1)}It should open file |term_in| for input from the
+  terminal. (The file |term_out| will already be open for output to the
+  terminal.)
+
+\textindent{2)}If the user has given a command line, this line should be
+  considered the first line of terminal input. Otherwise the
+  user should be prompted with `\.{**}', and the first line of input
+  should be whatever is typed in response.
+
+\textindent{3)}The first line of input, which might or might not be a
+  command line, should appear in locations |first| to |last-1| of the
+  |buffer| array.
+
+\textindent{4)}The global variable |loc| should be set so that the
+  character to be read next by \MP\ is in |buffer[loc]|. This
+  character should not be blank, and we should have |loc<last|.
+
+\yskip\noindent(It may be necessary to prompt the user several times
+before a non-blank line comes in. The prompt is `\.{**}' instead of the
+later `\.*' because the meaning is slightly different: `\.{input}' need
+not be typed immediately after~`\.{**}'.)
+
+@d loc mp->cur_input.loc_field /* location of first unread character in |buffer| */
+
+@ The following program does the required initialization
+without retrieving a possible command line.
+It should be clear how to modify this routine to deal with command lines,
+if the system permits them.
+@^system dependencies@>
+
+@c 
+boolean mp_init_terminal (MP mp) { /* gets the terminal input started */
+  t_open_in; 
+  if (mp->last!=0) {
+    loc = mp->first = 0;
+	return true;
+  }
+  while (1) { 
+    wake_up_terminal; do_fprintf(mp->term_out,"**"); update_terminal;
+@.**@>
+    if ( ! mp_input_ln(mp, mp->term_in ) ) { /* this shouldn't happen */
+      do_fprintf(mp->term_out,"\n! End of file on the terminal... why?");
+@.End of file on the terminal@>
+      return false;
+    }
+    loc=mp->first;
+    while ( (loc<(int)mp->last)&&(mp->buffer[loc]==' ') ) 
+      incr(loc);
+    if ( loc<(int)mp->last ) { 
+      return true; /* return unless the line was all blank */
+    };
+    do_fprintf(mp->term_out,"Please type the name of your input file.\n");
+  }
+}
+
+@ @<Declarations@>=
+boolean mp_init_terminal (MP mp) ;
+
+@ The symbolic names for internal quantities are put into \MP's hash table
+by using a routine called |primitive|, which will be defined later. Let us
+enter them now, so that we don't have to list all those names again
+anywhere else.
+
+@<Put each of \MP's primitives into the hash table@>=
+mp_primitive(mp, "tracingtitles",internal_quantity,mp_tracing_titles);
+@:tracingtitles_}{\&{tracingtitles} primitive@>
+mp_primitive(mp, "tracingequations",internal_quantity,mp_tracing_equations);
+@:mp_tracing_equations_}{\&{tracingequations} primitive@>
+mp_primitive(mp, "tracingcapsules",internal_quantity,mp_tracing_capsules);
+@:mp_tracing_capsules_}{\&{tracingcapsules} primitive@>
+mp_primitive(mp, "tracingchoices",internal_quantity,mp_tracing_choices);
+@:mp_tracing_choices_}{\&{tracingchoices} primitive@>
+mp_primitive(mp, "tracingspecs",internal_quantity,mp_tracing_specs);
+@:mp_tracing_specs_}{\&{tracingspecs} primitive@>
+mp_primitive(mp, "tracingcommands",internal_quantity,mp_tracing_commands);
+@:mp_tracing_commands_}{\&{tracingcommands} primitive@>
+mp_primitive(mp, "tracingrestores",internal_quantity,mp_tracing_restores);
+@:mp_tracing_restores_}{\&{tracingrestores} primitive@>
+mp_primitive(mp, "tracingmacros",internal_quantity,mp_tracing_macros);
+@:mp_tracing_macros_}{\&{tracingmacros} primitive@>
+mp_primitive(mp, "tracingoutput",internal_quantity,mp_tracing_output);
+@:mp_tracing_output_}{\&{tracingoutput} primitive@>
+mp_primitive(mp, "tracingstats",internal_quantity,mp_tracing_stats);
+@:mp_tracing_stats_}{\&{tracingstats} primitive@>
+mp_primitive(mp, "tracinglostchars",internal_quantity,mp_tracing_lost_chars);
+@:mp_tracing_lost_chars_}{\&{tracinglostchars} primitive@>
+mp_primitive(mp, "tracingonline",internal_quantity,mp_tracing_online);
+@:mp_tracing_online_}{\&{tracingonline} primitive@>
+mp_primitive(mp, "year",internal_quantity,mp_year);
+@:mp_year_}{\&{year} primitive@>
+mp_primitive(mp, "month",internal_quantity,mp_month);
+@:mp_month_}{\&{month} primitive@>
+mp_primitive(mp, "day",internal_quantity,mp_day);
+@:mp_day_}{\&{day} primitive@>
+mp_primitive(mp, "time",internal_quantity,mp_time);
+@:time_}{\&{time} primitive@>
+mp_primitive(mp, "charcode",internal_quantity,mp_char_code);
+@:mp_char_code_}{\&{charcode} primitive@>
+mp_primitive(mp, "charext",internal_quantity,mp_char_ext);
+@:mp_char_ext_}{\&{charext} primitive@>
+mp_primitive(mp, "charwd",internal_quantity,mp_char_wd);
+@:mp_char_wd_}{\&{charwd} primitive@>
+mp_primitive(mp, "charht",internal_quantity,mp_char_ht);
+@:mp_char_ht_}{\&{charht} primitive@>
+mp_primitive(mp, "chardp",internal_quantity,mp_char_dp);
+@:mp_char_dp_}{\&{chardp} primitive@>
+mp_primitive(mp, "charic",internal_quantity,mp_char_ic);
+@:mp_char_ic_}{\&{charic} primitive@>
+mp_primitive(mp, "designsize",internal_quantity,mp_design_size);
+@:mp_design_size_}{\&{designsize} primitive@>
+mp_primitive(mp, "pausing",internal_quantity,mp_pausing);
+@:mp_pausing_}{\&{pausing} primitive@>
+mp_primitive(mp, "showstopping",internal_quantity,mp_showstopping);
+@:mp_showstopping_}{\&{showstopping} primitive@>
+mp_primitive(mp, "fontmaking",internal_quantity,mp_fontmaking);
+@:mp_fontmaking_}{\&{fontmaking} primitive@>
+mp_primitive(mp, "linejoin",internal_quantity,mp_linejoin);
+@:mp_linejoin_}{\&{linejoin} primitive@>
+mp_primitive(mp, "linecap",internal_quantity,mp_linecap);
+@:mp_linecap_}{\&{linecap} primitive@>
+mp_primitive(mp, "miterlimit",internal_quantity,mp_miterlimit);
+@:mp_miterlimit_}{\&{miterlimit} primitive@>
+mp_primitive(mp, "warningcheck",internal_quantity,mp_warning_check);
+@:mp_warning_check_}{\&{warningcheck} primitive@>
+mp_primitive(mp, "boundarychar",internal_quantity,mp_boundary_char);
+@:mp_boundary_char_}{\&{boundarychar} primitive@>
+mp_primitive(mp, "prologues",internal_quantity,mp_prologues);
+@:mp_prologues_}{\&{prologues} primitive@>
+mp_primitive(mp, "truecorners",internal_quantity,mp_true_corners);
+@:mp_true_corners_}{\&{truecorners} primitive@>
+mp_primitive(mp, "mpprocset",internal_quantity,mp_procset);
+@:mp_procset_}{\&{mpprocset} primitive@>
+mp_primitive(mp, "troffmode",internal_quantity,mp_gtroffmode);
+@:troffmode_}{\&{troffmode} primitive@>
+mp_primitive(mp, "defaultcolormodel",internal_quantity,mp_default_color_model);
+@:mp_default_color_model_}{\&{defaultcolormodel} primitive@>
+mp_primitive(mp, "restoreclipcolor",internal_quantity,mp_restore_clip_color);
+@:mp_restore_clip_color_}{\&{restoreclipcolor} primitive@>
+
+@* \[47] Debugging.
+Once \MP\ is working, you should be able to diagnose most errors with
+the \.{show} commands and other diagnostic features. But for the initial
+stages of debugging, and for the revelation of really deep mysteries, you
+can compile \MP\ with a few more aids. An additional routine called |debug_help|
+will also come into play when you type `\.D' after an error message;
+|debug_help| also occurs just before a fatal error causes \MP\ to succumb.
+@^debugging@>
+@^system dependencies@>
+
+The interface to |debug_help| is primitive, but it is good enough when used
+with a debugger that allows you to set breakpoints and to read
+variables and change their values. After getting the prompt `\.{debug \#}', you
+type either a negative number (this exits |debug_help|), or zero (this
+goes to a location where you can set a breakpoint, thereby entering into
+dialog with the debugger), or a positive number |m| followed by
+an argument |n|. The meaning of |m| and |n| will be clear from the
+program below. (If |m=13|, there is an additional argument, |l|.)
+@.debug \#@>
+
+@<Last-minute...@>=
+void mp_debug_help (MP mp) { /* routine to display various things */
+  integer k;
+  int l,m,n;
+  char *aline;
+  size_t len;
+  while (1) { 
+    wake_up_terminal;
+    mp_print_nl(mp, "debug # (-1 to exit):"); update_terminal;
+@.debug \#@>
+    m = 0;
+    aline = (mp->read_ascii_file)(mp->term_in, &len);
+    if (len) { sscanf(aline,"%i",&m); xfree(aline); }
+    if ( m<=0 )
+      return;
+    n = 0 ;
+    aline = (mp->read_ascii_file)(mp->term_in, &len);
+    if (len) { sscanf(aline,"%i",&n); xfree(aline); }
+    switch (m) {
+    @<Numbered cases for |debug_help|@>;
+    default: mp_print(mp, "?"); break;
+    }
+  }
+}
+
+@ @<Numbered cases...@>=
+case 1: mp_print_word(mp, mp->mem[n]); /* display |mem[n]| in all forms */
+  break;
+case 2: mp_print_int(mp, info(n));
+  break;
+case 3: mp_print_int(mp, link(n));
+  break;
+case 4: mp_print_int(mp, eq_type(n)); mp_print_char(mp, ':'); mp_print_int(mp, equiv(n));
+  break;
+case 5: mp_print_variable_name(mp, n);
+  break;
+case 6: mp_print_int(mp, mp->internal[n]);
+  break;
+case 7: mp_do_show_dependencies(mp);
+  break;
+case 9: mp_show_token_list(mp, n,null,100000,0);
+  break;
+case 10: mp_print_str(mp, n);
+  break;
+case 11: mp_check_mem(mp, n>0); /* check wellformedness; print new busy locations if |n>0| */
+  break;
+case 12: mp_search_mem(mp, n); /* look for pointers to |n| */
+  break;
+case 13: 
+  l = 0;  
+  aline = (mp->read_ascii_file)(mp->term_in, &len);
+  if (len) { sscanf(aline,"%i",&l); xfree(aline); }
+  mp_print_cmd_mod(mp, n,l); 
+  break;
+case 14: for (k=0;k<=n;k++) mp_print_str(mp, mp->buffer[k]);
+  break;
+case 15: mp->panicking=! mp->panicking;
+  break;
+
+
+@ Saving the filename template
+
+@<Save the filename template@>=
+{ 
+  if ( mp->filename_template!=0 ) delete_str_ref(mp->filename_template);
+  if ( length(mp->cur_exp)==0 ) mp->filename_template=0;
+  else { 
+    mp->filename_template=mp->cur_exp; add_str_ref(mp->filename_template);
+  }
+}
+
+@* \[48] System-dependent changes.
+This section should be replaced, if necessary, by any special
+modification of the program
+that are necessary to make \MP\ work at a particular installation.
+It is usually best to design your change file so that all changes to
+previous sections preserve the section numbering; then everybody's version
+will be consistent with the published program. More extensive changes,
+which introduce new sections, can be inserted here; then only the index
+itself will get a new section number.
+@^system dependencies@>
+
+@* \[49] Index.
+Here is where you can find all uses of each identifier in the program,
+with underlined entries pointing to where the identifier was defined.
+If the identifier is only one letter long, however, you get to see only
+the underlined entries. {\sl All references are to section numbers instead of
+page numbers.}
+
+This index also lists error messages and other aspects of the program
+that you might want to look up some day. For example, the entry
+for ``system dependencies'' lists all sections that should receive
+special attention from people who are installing \MP\ in a new
+operating environment. A list of various things that can't happen appears
+under ``this can't happen''.
+Approximately 25 sections are listed under ``inner loop''; these account
+for more than 60\pct! of \MP's running time, exclusive of input and output.
diff --git a/test/unit/cweb_test.rb b/test/unit/cweb_test.rb
new file mode 100644
index 0000000..0044a92
--- /dev/null
+++ b/test/unit/cweb_test.rb
@@ -0,0 +1,7 @@
+require File.dirname(__FILE__) + '/../test_helper'
+
+class Ohcount::CWebTest < Ohcount::Test
+	def test_comprehensive
+		verify_parse("cweb.w")
+	end
+end
-- 
2.32.0.93.g670b81a890