=================================================================== RCS file: /cvs/mandoc/eqn.c,v retrieving revision 1.14 retrieving revision 1.22 diff -u -p -r1.14 -r1.22 --- mandoc/eqn.c 2011/07/21 11:57:56 1.14 +++ mandoc/eqn.c 2011/07/22 00:16:37 1.22 @@ -1,4 +1,4 @@ -/* $Id: eqn.c,v 1.14 2011/07/21 11:57:56 kristaps Exp $ */ +/* $Id: eqn.c,v 1.22 2011/07/22 00:16:37 kristaps Exp $ */ /* * Copyright (c) 2011 Kristaps Dzonsons * @@ -19,6 +19,7 @@ #endif #include +#include #include #include #include @@ -31,9 +32,20 @@ #define EQN_NEST_MAX 128 /* maximum nesting of defines */ #define EQN_MSG(t, x) mandoc_msg((t), (x)->parse, (x)->eqn.ln, (x)->eqn.pos, NULL) -struct eqnpart { +enum eqn_rest { + EQN_DESCOPE, + EQN_ERR, + EQN_OK, + EQN_EOF +}; + +struct eqnstr { const char *name; size_t sz; +}; + +struct eqnpart { + struct eqnstr str; int (*fp)(struct eqn_node *); }; @@ -44,6 +56,7 @@ enum eqnpartt { EQN__MAX }; +static struct eqn_box *eqn_box_alloc(struct eqn_box *); static void eqn_box_free(struct eqn_box *); static struct eqn_def *eqn_def_find(struct eqn_node *, const char *, size_t); @@ -54,14 +67,51 @@ static const char *eqn_nexttok(struct eqn_node *, size static const char *eqn_nextrawtok(struct eqn_node *, size_t *); static const char *eqn_next(struct eqn_node *, char, size_t *, int); -static int eqn_box(struct eqn_node *, struct eqn_box *); +static void eqn_rewind(struct eqn_node *); +static enum eqn_rest eqn_eqn(struct eqn_node *, struct eqn_box *); +static enum eqn_rest eqn_box(struct eqn_node *, struct eqn_box *); static const struct eqnpart eqnparts[EQN__MAX] = { - { "define", 6, eqn_do_define }, /* EQN_DEFINE */ - { "set", 3, eqn_do_set }, /* EQN_SET */ - { "undef", 5, eqn_do_undef }, /* EQN_UNDEF */ + { { "define", 6 }, eqn_do_define }, /* EQN_DEFINE */ + { { "set", 3 }, eqn_do_set }, /* EQN_SET */ + { { "undef", 5 }, eqn_do_undef }, /* EQN_UNDEF */ }; +static const struct eqnstr eqnmarks[EQNMARK__MAX] = { + { "", 0 }, /* EQNMARK_NONE */ + { "dot", 3 }, /* EQNMARK_DOT */ + { "dotdot", 6 }, /* EQNMARK_DOTDOT */ + { "hat", 3 }, /* EQNMARK_HAT */ + { "tilde", 5 }, /* EQNMARK_TILDE */ + { "vec", 3 }, /* EQNMARK_VEC */ + { "dyad", 4 }, /* EQNMARK_DYAD */ + { "bar", 3 }, /* EQNMARK_BAR */ + { "under", 5 }, /* EQNMARK_UNDER */ +}; + +static const struct eqnstr eqnfonts[EQNFONT__MAX] = { + { "", 0 }, /* EQNFONT_NONE */ + { "roman", 5 }, /* EQNFONT_ROMAN */ + { "bold", 4 }, /* EQNFONT_BOLD */ + { "italic", 6 }, /* EQNFONT_ITALIC */ +}; + +static const struct eqnstr eqnposs[EQNPOS__MAX] = { + { "", 0 }, /* EQNPOS_NONE */ + { "over", 4 }, /* EQNPOS_OVER */ + { "sup", 3 }, /* EQNPOS_SUP */ + { "sub", 3 }, /* EQNPOS_SUB */ + { "to", 2 }, /* EQNPOS_TO */ + { "from", 4 }, /* EQNPOS_FROM */ +}; + +static const struct eqnstr eqnpiles[EQNPILE__MAX] = { + { "", 0 }, /* EQNPILE_NONE */ + { "cpile", 5 }, /* EQNPILE_CPILE */ + { "rpile", 5 }, /* EQNPILE_RPILE */ + { "lpile", 5 }, /* EQNPILE_LPILE */ +}; + /* ARGSUSED */ enum rofferr eqn_read(struct eqn_node **epp, int ln, @@ -120,61 +170,211 @@ enum rofferr eqn_end(struct eqn_node *ep) { struct eqn_box *root; + enum eqn_rest c; - ep->eqn.root = root = - mandoc_calloc(1, sizeof(struct eqn_box)); + ep->eqn.root = mandoc_calloc(1, sizeof(struct eqn_box)); + + root = ep->eqn.root; root->type = EQN_ROOT; if (0 == ep->sz) return(ROFF_IGN); - /* - * Validate the expression. - * Use the grammar found in the literature. - */ + if (EQN_DESCOPE == (c = eqn_eqn(ep, root))) { + EQN_MSG(MANDOCERR_EQNNSCOPE, ep); + c = EQN_ERR; + } - return(eqn_box(ep, root) < 0 ? ROFF_IGN : ROFF_EQN); + return(EQN_EOF == c ? ROFF_EQN : ROFF_IGN); } -static int +static enum eqn_rest +eqn_eqn(struct eqn_node *ep, struct eqn_box *last) +{ + struct eqn_box *bp; + enum eqn_rest c; + + bp = eqn_box_alloc(last); + bp->type = EQN_SUBEXPR; + + while (EQN_OK == (c = eqn_box(ep, bp))) + /* Spin! */ ; + + return(c); +} + +static enum eqn_rest eqn_box(struct eqn_node *ep, struct eqn_box *last) { size_t sz; const char *start; - int i, nextc; + char *left; + enum eqn_rest c; + int i, size; struct eqn_box *bp; - nextc = 1; -again: if (NULL == (start = eqn_nexttok(ep, &sz))) - return(0); + return(EQN_EOF); + if (1 == sz && 0 == strncmp("}", start, 1)) + return(EQN_DESCOPE); + else if (5 == sz && 0 == strncmp("right", start, 5)) + return(EQN_DESCOPE); + else if (5 == sz && 0 == strncmp("above", start, 5)) + return(EQN_DESCOPE); + for (i = 0; i < (int)EQN__MAX; i++) { - if (eqnparts[i].sz != sz) + if (eqnparts[i].str.sz != sz) continue; - if (strncmp(eqnparts[i].name, start, sz)) + if (strncmp(eqnparts[i].str.name, start, sz)) continue; - if ( ! (*eqnparts[i].fp)(ep)) - return(-1); + return((*eqnparts[i].fp)(ep) ? EQN_OK : EQN_ERR); + } - goto again; + if (1 == sz && 0 == strncmp("{", start, 1)) { + if (EQN_DESCOPE != (c = eqn_eqn(ep, last))) { + if (EQN_ERR != c) + EQN_MSG(MANDOCERR_EQNSCOPE, ep); + return(EQN_ERR); + } + eqn_rewind(ep); + start = eqn_nexttok(ep, &sz); + assert(start); + if (1 == sz && 0 == strncmp("}", start, 1)) + return(EQN_OK); + EQN_MSG(MANDOCERR_EQNBADSCOPE, ep); + return(EQN_ERR); } - bp = mandoc_calloc(1, sizeof(struct eqn_box)); - bp->type = EQN_TEXT; + for (i = 0; i < (int)EQNPILE__MAX; i++) { + if (eqnpiles[i].sz != sz) + continue; + if (strncmp(eqnpiles[i].name, start, sz)) + continue; + if (NULL == (start = eqn_nexttok(ep, &sz))) { + EQN_MSG(MANDOCERR_EQNEOF, ep); + return(EQN_ERR); + } + if (1 != sz || strncmp("{", start, 1)) { + EQN_MSG(MANDOCERR_EQNSYNT, ep); + return(EQN_ERR); + } - if (nextc) - last->child = bp; - else - last->next = bp; + while (EQN_DESCOPE == (c = eqn_eqn(ep, last))) { + assert(last->last); + last->last->pile = (enum eqn_pilet)i; + eqn_rewind(ep); + start = eqn_nexttok(ep, &sz); + assert(start); + if (5 != sz || strncmp("above", start, 5)) + break; + last->last->above = 1; + } - bp->text = mandoc_malloc(sz + 1); - *bp->text = '\0'; - strlcat(bp->text, start, sz + 1); + if (EQN_DESCOPE != c) { + if (EQN_ERR != c) + EQN_MSG(MANDOCERR_EQNSCOPE, ep); + return(EQN_ERR); + } - last = bp; - nextc = 0; - goto again; + eqn_rewind(ep); + start = eqn_nexttok(ep, &sz); + assert(start); + if (1 == sz && 0 == strncmp("}", start, 1)) + return(EQN_OK); + + EQN_MSG(MANDOCERR_EQNBADSCOPE, ep); + return(EQN_ERR); + } + + if (4 == sz && 0 == strncmp("left", start, 4)) { + if (NULL == (start = eqn_nexttok(ep, &sz))) { + EQN_MSG(MANDOCERR_EQNEOF, ep); + return(EQN_ERR); + } + left = mandoc_strndup(start, sz); + if (EQN_DESCOPE != (c = eqn_eqn(ep, last))) + return(c); + assert(last->last); + last->last->left = left; + eqn_rewind(ep); + start = eqn_nexttok(ep, &sz); + assert(start); + if (5 != sz || strncmp("right", start, 5)) + return(EQN_DESCOPE); + if (NULL == (start = eqn_nexttok(ep, &sz))) { + EQN_MSG(MANDOCERR_EQNEOF, ep); + return(EQN_ERR); + } + last->last->right = mandoc_strndup(start, sz); + return(EQN_OK); + } + + for (i = 0; i < (int)EQNPOS__MAX; i++) { + if (eqnposs[i].sz != sz) + continue; + if (strncmp(eqnposs[i].name, start, sz)) + continue; + if (NULL == last->last) { + EQN_MSG(MANDOCERR_EQNSYNT, ep); + return(EQN_ERR); + } + last->last->pos = (enum eqn_post)i; + if (EQN_EOF == (c = eqn_box(ep, last))) { + EQN_MSG(MANDOCERR_EQNEOF, ep); + return(EQN_ERR); + } + return(c); + } + + for (i = 0; i < (int)EQNMARK__MAX; i++) { + if (eqnmarks[i].sz != sz) + continue; + if (strncmp(eqnmarks[i].name, start, sz)) + continue; + if (NULL == last->last) { + EQN_MSG(MANDOCERR_EQNSYNT, ep); + return(EQN_ERR); + } + last->last->mark = (enum eqn_markt)i; + if (EQN_EOF == (c = eqn_box(ep, last))) { + EQN_MSG(MANDOCERR_EQNEOF, ep); + return(EQN_ERR); + } + return(c); + } + + for (i = 0; i < (int)EQNFONT__MAX; i++) { + if (eqnfonts[i].sz != sz) + continue; + if (strncmp(eqnfonts[i].name, start, sz)) + continue; + if (EQN_EOF == (c = eqn_box(ep, last))) { + EQN_MSG(MANDOCERR_EQNEOF, ep); + return(EQN_ERR); + } else if (EQN_OK == c) + last->last->font = (enum eqn_fontt)i; + return(c); + } + + if (4 == sz && 0 == strncmp("size", start, 4)) { + if (NULL == (start = eqn_nexttok(ep, &sz))) { + EQN_MSG(MANDOCERR_EQNEOF, ep); + return(EQN_ERR); + } + size = mandoc_strntoi(start, sz, 10); + if (EQN_EOF == (c = eqn_box(ep, last))) { + EQN_MSG(MANDOCERR_EQNEOF, ep); + return(EQN_ERR); + } else if (EQN_OK != c) + return(c); + last->last->size = size; + } + + bp = eqn_box_alloc(last); + bp->type = EQN_TEXT; + bp->text = mandoc_strndup(start, sz); + return(EQN_OK); } void @@ -194,16 +394,36 @@ eqn_free(struct eqn_node *p) free(p); } +static struct eqn_box * +eqn_box_alloc(struct eqn_box *parent) +{ + struct eqn_box *bp; + + bp = mandoc_calloc(1, sizeof(struct eqn_box)); + bp->parent = parent; + bp->size = EQN_DEFSIZE; + + if (NULL == parent->first) + parent->first = bp; + else + parent->last->next = bp; + + parent->last = bp; + return(bp); +} + static void eqn_box_free(struct eqn_box *bp) { - if (bp->child) - eqn_box_free(bp->child); + if (bp->first) + eqn_box_free(bp->first); if (bp->next) eqn_box_free(bp->next); free(bp->text); + free(bp->left); + free(bp->right); free(bp); } @@ -221,19 +441,26 @@ eqn_nexttok(struct eqn_node *ep, size_t *sz) return(eqn_next(ep, '"', sz, 1)); } +static void +eqn_rewind(struct eqn_node *ep) +{ + + ep->cur = ep->rew; +} + static const char * eqn_next(struct eqn_node *ep, char quote, size_t *sz, int repl) { char *start, *next; int q, diff, lim; - size_t sv, ssz; + size_t ssz, dummy; struct eqn_def *def; if (NULL == sz) - sz = &ssz; + sz = &dummy; lim = 0; - sv = ep->cur; + ep->rew = ep->cur; again: /* Prevent self-definitions. */ @@ -242,7 +469,7 @@ again: return(NULL); } - ep->cur = sv; + ep->cur = ep->rew; start = &ep->data[(int)ep->cur]; q = 0; @@ -255,14 +482,26 @@ again: } start = &ep->data[(int)ep->cur]; - next = q ? strchr(start, quote) : strchr(start, ' '); + if ( ! q) { + if ('{' == *start || '}' == *start) + ssz = 1; + else + ssz = strcspn(start + 1, " ~\"{}\t") + 1; + next = start + (int)ssz; + if ('\0' == *next) + next = NULL; + } else + next = strchr(start, quote); + if (NULL != next) { *sz = (size_t)(next - start); ep->cur += *sz; if (q) ep->cur++; - while (' ' == ep->data[(int)ep->cur]) + while (' ' == ep->data[(int)ep->cur] || + '\t' == ep->data[(int)ep->cur] || + '~' == ep->data[(int)ep->cur]) ep->cur++; } else { if (q) @@ -284,7 +523,7 @@ again: ep->sz += diff; ep->data = mandoc_realloc(ep->data, ep->sz + 1); ep->data[ep->sz] = '\0'; - start = &ep->data[(int)sv]; + start = &ep->data[(int)ep->rew]; } diff = def->valsz - *sz;