isomorfeus-ferret 0.17.3 → 0.17.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: fb825b23a8f4d4422995bd20a52c24fd554c552352ba47e1af7059af60cacd33
-  data.tar.gz: 565707f28c6ea121d2c37b77c95d9a63f4c9a6ec663c5c0c96f59c499ca26f84
+  metadata.gz: 5aa89943933ef18acbb6c1c12e6da3ef85e037cc41740f506c320510406e765f
+  data.tar.gz: 7ade42fb44635b0b4dadc40b4376142597849eb76abf474b807a54f7f97d92c5
 SHA512:
-  metadata.gz: 3f907b655cdb94f7b69422da855b0972229cf37170e4ede27ded73ae46c77f7e16745e5d1a86856e40bc4e73dda042dccd921fd3f2757e76b8ffbedffa33bbdb
-  data.tar.gz: ab559729203ecc983ab1fb32e8efa584110e4d5ea30f0ddacead13613138453287370244a4845dc01df222c5e0685537468f16a90a3c271e28b69fb8b95e5f58
+  metadata.gz: d412050da5b223cd394378bd7fcca7daa4e9ebcf41f51264fc3f48930ff70ffe013731c2192ff4750f4236f30dd77432c9735dc1d19b03c3e220f9a5a611a3c5
+  data.tar.gz: 5bf17019a13fafcdf14124cc47587ca720dd908840f12fc90306899e2728b35d1a493ef683f2a5638105cd5d2c8bf840beaf552a7d75fa724f0ae14199ae5b42

data/ext/isomorfeus_ferret_ext/frb_index.c

@@ -653,21 +653,14 @@ static VALUE frb_tde_seek_te(VALUE self, VALUE rterm_enum) {
     return self;
 }
 
-/*
- *  call-seq:
- *     term_doc_enum.doc -> doc_id
- *
- *  Returns the current document number pointed to by the +term_doc_enum+.
+/*  Returns the current document number pointed to by the +term_doc_enum+.
  */
-static VALUE frb_tde_doc(VALUE self) {
+static VALUE frb_tde_doc_num(VALUE self) {
     FrtTermDocEnum *tde = (FrtTermDocEnum *)DATA_PTR(self);
     return INT2FIX(tde->doc_num(tde));
 }
 
 /*
- *  call-seq:
- *     term_doc_enum.doc -> doc_id
- *
  *  Returns the frequency of the current document pointed to by the
  *  +term_doc_enum+.
  */
@@ -676,11 +669,7 @@ static VALUE frb_tde_freq(VALUE self) {
     return INT2FIX(tde->freq(tde));
 }
 
-/*
- *  call-seq:
- *     term_doc_enum.doc -> doc_id
- *
- *  Move forward to the next document in the enumeration. Returns +true+ if
+/*  Move forward to the next document in the enumeration. Returns +true+ if
  *  there is another document or +false+ otherwise.
  */
 static VALUE frb_tde_next(VALUE self) {
@@ -688,11 +677,7 @@ static VALUE frb_tde_next(VALUE self) {
     return tde->next(tde) ? Qtrue : Qfalse;
 }
 
-/*
- *  call-seq:
- *     term_doc_enum.doc -> doc_id
- *
- *  Move forward to the next document in the enumeration. Returns +true+ if
+/*  Move forward to the next document in the enumeration. Returns +true+ if
  *  there is another document or +false+ otherwise.
  */
 static VALUE frb_tde_next_position(VALUE self) {
@@ -709,7 +694,7 @@ static VALUE frb_tde_next_position(VALUE self) {
 
 /*
  *  call-seq:
- *     term_doc_enum.each {|doc_id, freq| do_something() } -> doc_count
+ *     term_doc_enum.each {|doc_num, freq| do_something() } -> doc_count
  *
  *  Iterate through the documents and document frequencies in the
  *  +term_doc_enum+.
@@ -821,8 +806,8 @@ static VALUE frb_tde_to_json(int argc, VALUE *argv, VALUE self) {
  *  used within the each method. For example, to print the terms documents and
  *  positions;
  *
- *    tde.each do |doc_id, freq|
- *      puts "term appeared #{freq} times in document #{doc_id}:"
+ *    tde.each do |doc_num, freq|
+ *      puts "term appeared #{freq} times in document #{doc_num}:"
  *      positions = []
  *      tde.each_position {|pos| positions << pos}
  *      puts "  #{positions.join(', ')}"
@@ -1796,20 +1781,20 @@ static VALUE frb_ir_init(VALUE self, VALUE rdir) {
 
 /*
  *  call-seq:
- *     index_reader.set_norm(doc_id, field, val)
+ *     index_reader.set_norm(doc_num, field, val)
  *
- *  Expert: change the boost value for a +field+ in document at +doc_id+.
+ *  Expert: change the boost value for a +field+ in document at +doc_num+.
  *  +val+ should be an integer in the range 0..255 which corresponds to an
  *  encoded float value.
  */
 static VALUE
-frb_ir_set_norm(VALUE self, VALUE rdoc_id, VALUE rfield, VALUE rval) {
+frb_ir_set_norm(VALUE self, VALUE rdoc_num, VALUE rfield, VALUE rval) {
     int ex_code = 0;
     const char *msg = NULL;
     FrtIndexReader *ir = (FrtIndexReader *)DATA_PTR(self);
 
     FRT_TRY
-        frt_ir_set_norm(ir, FIX2INT(rdoc_id), frb_field(rfield), (frt_uchar)NUM2CHR(rval));
+        frt_ir_set_norm(ir, FIX2INT(rdoc_num), frb_field(rfield), (frt_uchar)NUM2CHR(rval));
     FRT_XCATCHALL
         ex_code = xcontext.excode;
         msg = xcontext.msg;
@@ -1837,7 +1822,7 @@ frb_ir_norms(VALUE self, VALUE rfield) {
     frt_uchar *norms;
     norms = frt_ir_get_norms(ir, frb_field(rfield));
     if (norms) {
-        return rb_str_new((char *)norms, ir->max_doc(ir));
+        return rb_str_new((char *)norms, ir->max_doc_num(ir));
     } else {
         return Qnil;
     }
@@ -1855,11 +1840,11 @@ frb_ir_get_norms_into(VALUE self, VALUE rfield, VALUE rnorms, VALUE roffset) {
     int offset;
     offset = FIX2INT(roffset);
     Check_Type(rnorms, T_STRING);
-    if (RSTRING_LEN(rnorms) < offset + ir->max_doc(ir)) {
+    if (RSTRING_LEN(rnorms) < offset + ir->max_doc_num(ir)) {
         rb_raise(rb_eArgError, "supplied a string of length:%ld to "
                  "IndexReader#get_norms_into but needed a string of length "
                  "offset:%d + maxdoc:%d",
-                 RSTRING_LEN(rnorms), offset, ir->max_doc(ir));
+                 RSTRING_LEN(rnorms), offset, ir->max_doc_num(ir));
     }
 
     frt_ir_get_norms_into(ir, frb_field(rfield),
@@ -1927,22 +1912,21 @@ frb_ir_has_deletions(VALUE self) {
     return ir->has_deletions(ir) ? Qtrue : Qfalse;
 }
 
-/*
- *  call-seq:
- *     index_reader.delete(doc_id) -> index_reader
+/*  call-seq:
+ *     index_reader.delete(doc_num) -> index_reader
  *
- *  Delete document referenced internally by document id +doc_id+. The
+ *  Delete document referenced internally by document id +doc_num+. The
  *  document_id is the number used to reference documents in the index and is
  *  returned by search methods.
  */
 static VALUE
-frb_ir_delete(VALUE self, VALUE rdoc_id) {
+frb_ir_delete(VALUE self, VALUE rdoc_num) {
     int ex_code = 0;
     const char *msg = NULL;
     FrtIndexReader *ir = (FrtIndexReader *)DATA_PTR(self);
 
     FRT_TRY
-        frt_ir_delete_doc(ir, FIX2INT(rdoc_id));
+        frt_ir_delete_doc(ir, FIX2INT(rdoc_num));
     FRT_XCATCHALL
         ex_code = xcontext.excode;
         msg = xcontext.msg;
@@ -1956,31 +1940,30 @@ frb_ir_delete(VALUE self, VALUE rdoc_id) {
     return self;
 }
 
-/*
- *  call-seq:
- *     index_reader.deleted?(doc_id) -> bool
+/* call-seq:
+ *     index_reader.deleted?(doc_num) -> bool
  *
- *  Returns true if the document at +doc_id+ has been deleted.
+ *  Returns true if the document at +doc_num+ has been deleted.
  */
 static VALUE
-frb_ir_is_deleted(VALUE self, VALUE rdoc_id) {
+frb_ir_is_deleted(VALUE self, VALUE rdoc_num) {
     FrtIndexReader *ir = (FrtIndexReader *)DATA_PTR(self);
-    return ir->is_deleted(ir, FIX2INT(rdoc_id)) ? Qtrue : Qfalse;
+    return ir->is_deleted(ir, FIX2INT(rdoc_num)) ? Qtrue : Qfalse;
 }
 
-/*
- *  call-seq:
+/*  call-seq:
  *     index_reader.max_doc -> number
  *
  *  Returns 1 + the maximum document id in the index. It is the
  *  document_id that will be used by the next document added to the index. If
  *  there are no deletions, this number also refers to the number of documents
  *  in the index.
+ *  TODO: Rename to next_doc_num?
  */
 static VALUE
-frb_ir_max_doc(VALUE self) {
+frb_ir_max_doc_num(VALUE self) {
     FrtIndexReader *ir = (FrtIndexReader *)DATA_PTR(self);
-    return INT2FIX(ir->max_doc(ir));
+    return INT2FIX(ir->max_doc_num(ir));
 }
 
 /*
@@ -2042,8 +2025,8 @@ frb_get_doc_range(FrtIndexReader *ir, int pos, int len, int max) {
 
 /*
  *  call-seq:
- *     index_reader.get_document(doc_id) -> LazyDoc
- *     index_reader[doc_id] -> LazyDoc
+ *     index_reader.get_document(doc_num) -> LazyDoc
+ *     index_reader[doc_num] -> LazyDoc
  *
  *  Retrieve a document from the index. See LazyDoc for more details on the
  *  document returned. Documents are referenced internally by document ids
@@ -2054,7 +2037,7 @@ frb_ir_get_doc(int argc, VALUE *argv, VALUE self) {
     FrtIndexReader *ir = (FrtIndexReader *)DATA_PTR(self);
     VALUE arg1, arg2;
     long pos, len;
-    long max = ir->max_doc(ir);
+    long max = ir->max_doc_num(ir);
     rb_scan_args(argc, argv, "11", &arg1, &arg2);
     if (argc == 1) {
         if (FIXNUM_P(arg1)) {
@@ -2117,19 +2100,18 @@ frb_ir_is_latest(VALUE self) {
     return frt_ir_is_latest(ir) ? Qtrue : Qfalse;
 }
 
-/*
- *  call-seq:
- *     index_reader.term_vector(doc_id, field) -> TermVector
+/*  call-seq:
+ *     index_reader.term_vector(doc_num, field) -> TermVector
  *
- *  Return the TermVector for the field +field+ in the document at +doc_id+ in
+ *  Return the TermVector for the field +field+ in the document at +doc_num+ in
  *  the index. Return nil if no such term_vector exists. See TermVector.
  */
 static VALUE
-frb_ir_term_vector(VALUE self, VALUE rdoc_id, VALUE rfield) {
+frb_ir_term_vector(VALUE self, VALUE rdoc_num, VALUE rfield) {
     FrtIndexReader *ir = (FrtIndexReader *)DATA_PTR(self);
     FrtTermVector *tv;
     VALUE rtv;
-    tv = ir->term_vector(ir, FIX2INT(rdoc_id), frb_field(rfield));
+    tv = ir->term_vector(ir, FIX2INT(rdoc_num), frb_field(rfield));
     if (tv) {
         rtv = frb_get_tv(tv);
         frt_tv_destroy(tv);
@@ -2144,18 +2126,17 @@ frb_add_each_tv(void *key, void *value, void *rtvs) {
     rb_hash_aset((VALUE)rtvs, ID2SYM((ID)key), frb_get_tv(value));
 }
 
-/*
- *  call-seq:
- *     index_reader.term_vectors(doc_id) -> hash of TermVector
+/*  call-seq:
+ *     index_reader.term_vectors(doc_num) -> hash of TermVector
  *
- *  Return the TermVectors for the document at +doc_id+ in the index. The
+ *  Return the TermVectors for the document at +doc_num+ in the index. The
  *  value returned is a hash of the TermVectors for each field in the document
  *  and they are referenced by field names (as symbols).
  */
 static VALUE
-frb_ir_term_vectors(VALUE self, VALUE rdoc_id) {
+frb_ir_term_vectors(VALUE self, VALUE rdoc_num) {
     FrtIndexReader *ir = (FrtIndexReader *)DATA_PTR(self);
-    FrtHash *tvs = ir->term_vectors(ir, FIX2INT(rdoc_id));
+    FrtHash *tvs = ir->term_vectors(ir, FIX2INT(rdoc_num));
     VALUE rtvs = rb_hash_new();
     frt_h_each(tvs, &frb_add_each_tv, (void *)rtvs);
     frt_h_destroy(tvs);
@@ -2359,11 +2340,11 @@ static VALUE frb_ir_each(VALUE self) {
         int ex_code = 0;
         const char *msg = NULL;
         long i;
-        long max_doc = ir->max_doc(ir);
+        int max_doc_num = ir->max_doc_num(ir);
         VALUE rld;
 
         FRT_TRY
-            for (i = 0; i < max_doc; i++) {
+            for (i = 0; i < max_doc_num; i++) {
                 if (ir->is_deleted(ir, i)) continue;
                 rld = frb_get_lazy_doc(ir->get_lazy_doc(ir, i));
                 rb_yield(rld);
@@ -2504,8 +2485,8 @@ Init_TermEnum(void) {
  *
  *    tde = index_reader.term_docs_for(:content, "fox")
  *
- *    tde.each do |doc_id, freq|
- *      puts "fox appeared #{freq} times in document #{doc_id}:"
+ *    tde.each do |doc_num, freq|
+ *      puts "fox appeared #{freq} times in document #{doc_num}:"
  *      positions = []
  *      tde.each_position {|pos| positions << pos}
  *      puts "  #{positions.join(', ')}"
@@ -2530,7 +2511,7 @@ static void Init_TermDocEnum(void) {
     rb_define_alloc_func(cTermDocEnum, frb_tde_alloc);
     rb_define_method(cTermDocEnum, "seek",           frb_tde_seek, 2);
     rb_define_method(cTermDocEnum, "seek_term_enum", frb_tde_seek_te, 1);
-    rb_define_method(cTermDocEnum, "doc",            frb_tde_doc, 0);
+    rb_define_method(cTermDocEnum, "doc_num",        frb_tde_doc_num, 0);
     rb_define_method(cTermDocEnum, "freq",           frb_tde_freq, 0);
     rb_define_method(cTermDocEnum, "next?",          frb_tde_next, 0);
     rb_define_method(cTermDocEnum, "next_position",  frb_tde_next_position, 0);
@@ -2599,7 +2580,7 @@ static void Init_TVTerm(void) {
  *
  *  == Example
  *
- *    tv = index_reader.term_vector(doc_id, :content)
+ *    tv = index_reader.term_vector(doc_num, :content)
  *    tv_term = tv.find {|tvt| tvt.term == "fox"}
  *
  *    # get the term frequency
@@ -2825,7 +2806,7 @@ void Init_IndexReader(void) {
     rb_define_method(cIndexReader, "has_deletions?", frb_ir_has_deletions, 0);
     rb_define_method(cIndexReader, "delete",         frb_ir_delete,        1);
     rb_define_method(cIndexReader, "deleted?",       frb_ir_is_deleted,    1);
-    rb_define_method(cIndexReader, "max_doc",        frb_ir_max_doc,       0);
+    rb_define_method(cIndexReader, "max_doc_num",    frb_ir_max_doc_num,   0);
     rb_define_method(cIndexReader, "num_docs",       frb_ir_num_docs,      0);
     rb_define_method(cIndexReader, "undelete_all",   frb_ir_undelete_all,  0);
     rb_define_method(cIndexReader, "latest?",        frb_ir_is_latest,     0);

data/ext/isomorfeus_ferret_ext/frb_search.c

@@ -93,7 +93,7 @@ static VALUE sym_integer;
 static VALUE sym_float;
 static VALUE sym_string;
 static VALUE sym_auto;
-static VALUE sym_doc_id;
+static VALUE sym_doc_num;
 static VALUE sym_score;
 static VALUE sym_byte;
 
@@ -146,7 +146,7 @@ extern VALUE frb_get_lazy_doc(FrtLazyDoc *lazy_doc);
  ****************************************************************************/
 
 static VALUE frb_get_hit(FrtHit *hit) {
-    return rb_struct_new(cHit, INT2FIX(hit->doc), rb_float_new((double)hit->score), NULL);
+    return rb_struct_new(cHit, INT2FIX(hit->doc_num), rb_float_new((double)hit->score), NULL);
 }
 
 /****************************************************************************
@@ -198,10 +198,10 @@ static VALUE frb_td_to_s(int argc, VALUE *argv, VALUE self) {
 
     for (i = 0; i < len; i++) {
         VALUE rhit = RARRAY_PTR(rhits)[i];
-        int doc_id = FIX2INT(rb_funcall(rhit, id_doc, 0));
+        int doc_num = FIX2INT(rb_funcall(rhit, id_doc, 0));
         const char *value = "";
         size_t value_len = 0;
-        FrtLazyDoc *lzd = sea->get_lazy_doc(sea, doc_id);
+        FrtLazyDoc *lzd = sea->get_lazy_doc(sea, doc_num);
         FrtLazyDocField *lzdf = frt_lazy_doc_get(lzd, field);
         if (NULL != lzdf) {
             value = frt_lazy_df_get_data(lzdf, 0);
@@ -212,7 +212,7 @@ static VALUE frb_td_to_s(int argc, VALUE *argv, VALUE self) {
             FRT_REALLOC_N(str, char, capa);
         }
 
-        sprintf(str + p, "\t%d \"%s\": %0.5f\n", doc_id, value,
+        sprintf(str + p, "\t%d \"%s\": %0.5f\n", doc_num, value,
                 NUM2DBL(rb_funcall(rhit, id_score, 0)));
         p += strlen(str + p);
         frt_lazy_doc_close(lzd);
@@ -279,7 +279,7 @@ static VALUE frb_td_to_json(VALUE self) {
 	FrtLazyDoc *lzd;
 	FrtSearcher *sea = (FrtSearcher *)DATA_PTR(rb_funcall(self, id_searcher, 0));
 	const int num_hits = RARRAY_LEN(rhits);
-	int doc_id;
+	int doc_num;
     int len = 32768;
 	char *str = FRT_ALLOC_N(char, len);
     char *s = str;
@@ -290,8 +290,8 @@ static VALUE frb_td_to_json(VALUE self) {
         if (i) *(s++) = ',';
         *(s++) = '{';
 		rhit = RARRAY_PTR(rhits)[i];
-		doc_id = FIX2INT(rb_funcall(rhit, id_doc, 0));
-		lzd = sea->get_lazy_doc(sea, doc_id);
+		doc_num = FIX2INT(rb_funcall(rhit, id_doc, 0));
+		lzd = sea->get_lazy_doc(sea, doc_num);
 		s = frb_lzd_load_to_json(lzd, &str, s, &len);
         frt_lazy_doc_close(lzd);
         *(s++) = '}';
@@ -2692,7 +2692,7 @@ static int get_sort_type(VALUE rtype) {
         return FRT_SORT_TYPE_STRING;
     } else if (rtype == sym_score) {
         return FRT_SORT_TYPE_SCORE;
-    } else if (rtype == sym_doc_id) {
+    } else if (rtype == sym_doc_num) {
         return FRT_SORT_TYPE_DOC;
     } else if (rtype == sym_float) {
         return FRT_SORT_TYPE_FLOAT;
@@ -2700,7 +2700,7 @@ static int get_sort_type(VALUE rtype) {
         return FRT_SORT_TYPE_AUTO;
     } else {
         rb_raise(rb_eArgError, ":%s is an unknown sort-type. Please choose "
-                 "from [:integer, :float, :string, :auto, :score, :doc_id]",
+                 "from [:integer, :float, :string, :auto, :score, :doc_num]",
                  rb_id2name(SYM2ID(rtype)));
     }
     return FRT_SORT_TYPE_DOC;
@@ -2717,7 +2717,7 @@ static int get_sort_type(VALUE rtype) {
  *
  *  :type::         Default: +:auto+. Specifies how a field should be sorted.
  *                  Choose from one of; +:auto+, +:integer+, +:float+,
- *                  +:string+, +:byte+, +:doc_id+ or +:score+. +:auto+ will
+ *                  +:string+, +:byte+, +:doc_num+ or +:score+. +:auto+ will
  *                  check the datatype of the field by trying to parse it into
  *                  either a number or a float before settling on a string
  *                  sort. String sort is locale dependent and works for
@@ -2786,7 +2786,7 @@ static VALUE frb_sf_get_name(VALUE self) {
  *     sort_field.type -> symbol
  *
  *  Return the type of sort. Should be one of; +:auto+, +:integer+, +:float+,
- *  +:string+, +:byte+, +:doc_id+ or +:score+.
+ *  +:string+, +:byte+, +:doc_num+ or +:score+.
  */
 static VALUE frb_sf_get_type(VALUE self) {
     GET_SF();
@@ -2796,7 +2796,7 @@ static VALUE frb_sf_get_type(VALUE self) {
         case FRT_SORT_TYPE_FLOAT:   return sym_float;
         case FRT_SORT_TYPE_STRING:  return sym_string;
         case FRT_SORT_TYPE_AUTO:    return sym_auto;
-        case FRT_SORT_TYPE_DOC:     return sym_doc_id;
+        case FRT_SORT_TYPE_DOC:     return sym_doc_num;
         case FRT_SORT_TYPE_SCORE:   return sym_score;
     }
     return Qnil;
@@ -2900,7 +2900,7 @@ static void frb_parse_sort_str(FrtSort *sort, char *xsort_str) {
 
         if (strcmp("SCORE", s) == 0) {
             sf = frt_sort_field_score_new(reverse);
-        } else if (strcmp("DOC_ID", s) == 0) {
+        } else if (strcmp("DOC_NUM", s) == 0) {
             sf = frt_sort_field_doc_new(reverse);
         } else {
             sf = frt_sort_field_auto_new(rb_intern(s), reverse);
@@ -2939,7 +2939,7 @@ static void frb_sort_add(FrtSort *sort, VALUE rsf, bool reverse) {
 #define GET_SORT() FrtSort *sort = (FrtSort *)DATA_PTR(self)
 /*
  *  call-seq:
- *     Sort.new(sort_fields = [SortField::SCORE, SortField::DOC_ID], reverse = false) -> Sort
+ *     Sort.new(sort_fields = [SortField::SCORE, SortField::DOC_NUM], reverse = false) -> Sort
  *
  *  Create a new Sort object. If +reverse+ is true, all sort_fields will be
  *  reversed so if any of them are already reversed the  will be turned back
@@ -3061,21 +3061,21 @@ static VALUE frb_sea_doc_freq(VALUE self, VALUE rfield, VALUE rterm) {
 
 /*
  *  call-seq:
- *     searcher.get_document(doc_id) -> LazyDoc
- *     searcher[doc_id] -> LazyDoc
+ *     searcher.get_document(doc_num) -> LazyDoc
+ *     searcher[doc_num] -> LazyDoc
  *
  *  Retrieve a document from the index. See LazyDoc for more details on the
  *  document returned. Documents are referenced internally by document ids
  *  which are returned by the Searchers search methods.
  */
-static VALUE frb_sea_doc(VALUE self, VALUE rdoc_id) {
+static VALUE frb_sea_doc(VALUE self, VALUE rdoc_num) {
     int ex_code = 0;
     const char *msg = NULL;
     GET_SEA();
     VALUE ld = Qnil;
 
     FRT_TRY
-        ld = frb_get_lazy_doc(sea->get_lazy_doc(sea, FIX2INT(rdoc_id)));
+        ld = frb_get_lazy_doc(sea->get_lazy_doc(sea, FIX2INT(rdoc_num)));
     FRT_XCATCHALL
         ex_code = xcontext.excode;
         msg = xcontext.msg;
@@ -3098,13 +3098,13 @@ static VALUE frb_sea_doc(VALUE self, VALUE rdoc_id) {
  *  there are no deletions, this number also refers to the number of documents
  *  in the index.
  */
-static VALUE frb_sea_max_doc(VALUE self) {
+static VALUE frb_sea_max_doc_num(VALUE self) {
     GET_SEA();
-    return INT2FIX(sea->max_doc(sea));
+    return INT2FIX(sea->max_doc_num(sea));
 }
 
-static float call_filter_proc(int doc_id, float score, FrtSearcher *sea, void *arg) {
-    VALUE val = rb_funcall((VALUE)arg, id_call, 3, INT2FIX(doc_id), rb_float_new((double)score), sea->rsea);
+static float call_filter_proc(int doc_num, float score, FrtSearcher *sea, void *arg) {
+    VALUE val = rb_funcall((VALUE)arg, id_call, 3, INT2FIX(doc_num), rb_float_new((double)score), sea->rsea);
     switch (TYPE(val)) {
         case T_NIL:
         case T_FALSE:
@@ -3261,7 +3261,7 @@ static FrtTopDocs *frb_sea_search_internal(FrtQuery *query, VALUE roptions, FrtS
  *                  to specify a fields type to sort it correctly. For more
  *                  on this, see the documentation for SortField
  *  :filter::       a Filter object to filter the search results with
- *  :filter_proc::  a filter Proc is a Proc which takes the doc_id, the score
+ *  :filter_proc::  a filter Proc is a Proc which takes the doc_num, the score
  *                  and the Searcher object as its parameters and returns
  *                  either a Boolean value specifying whether the result
  *                  should be included in the result set, or a Float between 0
@@ -3280,13 +3280,13 @@ static VALUE frb_sea_search(int argc, VALUE *argv, VALUE self) {
 
 /*
  *  call-seq:
- *     searcher.search_each(query, options = {}) {|doc_id, score| do_something}
+ *     searcher.search_each(query, options = {}) {|doc_num, score| do_something}
  *         -> total_hits
  *
  *  Run a query through the Searcher on the index. A TopDocs object is
  *  returned with the relevant results. The +query+ is a Query object. The
  *  Searcher#search_each method yields the internal document id (used to
- *  reference documents in the Searcher object like this; +searcher[doc_id]+)
+ *  reference documents in the Searcher object like this; +searcher[doc_num]+)
  *  and the search score for that document. It is possible for the score to be
  *  greater than 1.0 for some queries and taking boosts into account. This
  *  method will also normalize scores to the range 0.0..1.0 when the max-score
@@ -3314,7 +3314,7 @@ static VALUE frb_sea_search(int argc, VALUE *argv, VALUE self) {
  *                  to specify a fields type to sort it correctly. For more
  *                  on this, see the documentation for SortField
  *  :filter::       a Filter object to filter the search results with
- *  :filter_proc::  a filter Proc is a Proc which takes the doc_id, the score
+ *  :filter_proc::  a filter Proc is a Proc which takes the doc_num, the score
  *                  and the Searcher object as its parameters and returns a
  *                  Boolean value specifying whether the result should be
  *                  included in the result set.
@@ -3335,7 +3335,7 @@ static VALUE frb_sea_search_each(int argc, VALUE *argv, VALUE self) {
 
     /* yield normalized scores */
     for (i = 0; i < td->size; i++) {
-        rb_yield_values(2, INT2FIX(td->hits[i]->doc), rb_float_new((double)(td->hits[i]->score/max_score)));
+        rb_yield_values(2, INT2FIX(td->hits[i]->doc_num), rb_float_new((double)(td->hits[i]->score/max_score)));
     }
 
     rtotal_hits = INT2FIX(td->total_hits);
@@ -3430,14 +3430,14 @@ static VALUE frb_sea_scan(int argc, VALUE *argv, VALUE self) {
 
 /*
  *  call-seq:
- *     searcher.explain(query, doc_id) -> Explanation
+ *     searcher.explain(query, doc_num) -> Explanation
  *
  *  Create an explanation object to explain the score returned for a
- *  particular document at +doc_id+ in the index for the query +query+.
+ *  particular document at +doc_num+ in the index for the query +query+.
  *
  *  Usually used like this;
  *
- *    puts searcher.explain(query, doc_id).to_s
+ *    puts searcher.explain(query, doc_num).to_s
  */
 
 static size_t frb_explanation_size(const void *p) {
@@ -3468,17 +3468,17 @@ static VALUE frb_expl_alloc(VALUE rclass) {
     return TypedData_Wrap_Struct(rclass, &frb_explanation_t, e);
 }
 
-static VALUE frb_sea_explain(VALUE self, VALUE rquery, VALUE rdoc_id) {
+static VALUE frb_sea_explain(VALUE self, VALUE rquery, VALUE rdoc_num) {
     GET_SEA();
     FrtQuery *query = DATA_PTR(rquery);
     FrtExplanation *expl;
-    expl = sea->explain(sea, query, FIX2INT(rdoc_id));
+    expl = sea->explain(sea, query, FIX2INT(rdoc_num));
     return TypedData_Wrap_Struct(cExplanation, &frb_explanation_t, expl);
 }
 
 /*
  *  call-seq:
- *     searcher.highlight(query, doc_id, field, options = {}) -> Array
+ *     searcher.highlight(query, doc_num, field, options = {}) -> Array
  *
  *  Returns an array of strings with the matches highlighted.
  *
@@ -3500,7 +3500,7 @@ static VALUE frb_sea_explain(VALUE self, VALUE rquery, VALUE rdoc_id) {
  */
 static VALUE frb_sea_highlight(int argc, VALUE *argv, VALUE self) {
     GET_SEA();
-    VALUE rquery, rdoc_id, rfield, roptions, v;
+    VALUE rquery, rdoc_num, rfield, roptions, v;
     int excerpt_length = 150;
     int num_excerpts = 2;
     const char *pre_tag = "<b>";
@@ -3508,7 +3508,7 @@ static VALUE frb_sea_highlight(int argc, VALUE *argv, VALUE self) {
     const char *ellipsis = "...";
     char **excerpts;
 
-    rb_scan_args(argc, argv, "31", &rquery, &rdoc_id, &rfield, &roptions);
+    rb_scan_args(argc, argv, "31", &rquery, &rdoc_num, &rfield, &roptions);
     FrtQuery *query = DATA_PTR(rquery);
     if (argc > 3) {
         if (TYPE(roptions) != T_HASH) {
@@ -3538,7 +3538,7 @@ static VALUE frb_sea_highlight(int argc, VALUE *argv, VALUE self) {
 
     if ((excerpts = frt_searcher_highlight(sea,
                                        query,
-                                       FIX2INT(rdoc_id),
+                                       FIX2INT(rdoc_num),
                                        frb_field(rfield),
                                        excerpt_length,
                                        num_excerpts,
@@ -3869,7 +3869,7 @@ static void Init_TopDocs(void) {
  *
  *  == Example
  *
- *    puts searcher.explain(query, doc_id).to_s
+ *    puts searcher.explain(query, doc_num).to_s
  */
 static void Init_Explanation(void) {
     cExplanation = rb_define_class_under(mSearch, "Explanation", rb_cObject);
@@ -4748,7 +4748,7 @@ static void Init_Filter(void) {
  *  * :float
  *  * :string
  *  * :byte
- *  * :doc_id
+ *  * :doc_num
  *  * :score
  *
  *  The type of the SortField is set by passing it as a parameter to the
@@ -4784,7 +4784,7 @@ static void Init_SortField(void) {
     sym_float = ID2SYM(rb_intern("float"));
     sym_string = ID2SYM(rb_intern("string"));
     sym_auto = ID2SYM(rb_intern("auto"));
-    sym_doc_id = ID2SYM(rb_intern("doc_id"));
+    sym_doc_num = ID2SYM(rb_intern("doc_num"));
     sym_score = ID2SYM(rb_intern("score"));
     sym_byte = ID2SYM(rb_intern("byte"));
 
@@ -4804,12 +4804,12 @@ static void Init_SortField(void) {
     rb_define_const(cSortField, "SCORE_REV", TypedData_Wrap_Struct(cSortField, &frb_sort_field_t, FRT_SORT_FIELD_SCORE_REV));
     FRT_SORT_FIELD_SCORE_REV->rfield = rb_const_get(cSortField, rb_intern("SCORE_REV"));
 
-    rb_define_const(cSortField, "DOC_ID", TypedData_Wrap_Struct(cSortField, &frb_sort_field_t, FRT_SORT_FIELD_DOC));
-    oSORT_FIELD_DOC = rb_const_get(cSortField, rb_intern("DOC_ID"));
+    rb_define_const(cSortField, "DOC_NUM", TypedData_Wrap_Struct(cSortField, &frb_sort_field_t, FRT_SORT_FIELD_DOC));
+    oSORT_FIELD_DOC = rb_const_get(cSortField, rb_intern("DOC_NUM"));
     FRT_SORT_FIELD_DOC->rfield = oSORT_FIELD_DOC;
 
-    rb_define_const(cSortField, "DOC_ID_REV", TypedData_Wrap_Struct(cSortField, &frb_sort_field_t, FRT_SORT_FIELD_DOC_REV));
-    FRT_SORT_FIELD_DOC_REV->rfield = rb_const_get(cSortField, rb_intern("DOC_ID_REV"));
+    rb_define_const(cSortField, "DOC_NUM_REV", TypedData_Wrap_Struct(cSortField, &frb_sort_field_t, FRT_SORT_FIELD_DOC_REV));
+    FRT_SORT_FIELD_DOC_REV->rfield = rb_const_get(cSortField, rb_intern("DOC_NUM_REV"));
 }
 
 /*
@@ -4871,8 +4871,8 @@ static void Init_Sort(void) {
  *
  *    searcher.search_each(TermQuery.new(:content, "ferret")
  *                         :filter => RangeFilter.new(:date, :< => "2006"),
- *                         :sort => "date DESC, title") do |doc_id, score|
- *        puts "#{searcher[doc_id][title] scored #{score}"
+ *                         :sort => "date DESC, title") do |doc_num, score|
+ *        puts "#{searcher[doc_num][title] scored #{score}"
  *    end
  */
 static void Init_Searcher(void) {
@@ -4902,7 +4902,7 @@ static void Init_Searcher(void) {
     rb_define_method(cSearcher, "doc_freq", frb_sea_doc_freq, 2);
     rb_define_method(cSearcher, "get_document", frb_sea_doc, 1);
     rb_define_method(cSearcher, "[]", frb_sea_doc, 1);
-    rb_define_method(cSearcher, "max_doc", frb_sea_max_doc, 0);
+    rb_define_method(cSearcher, "max_doc_num", frb_sea_max_doc_num, 0);
     rb_define_method(cSearcher, "search", frb_sea_search, -1);
     rb_define_method(cSearcher, "search_each", frb_sea_search_each, -1);
     rb_define_method(cSearcher, "scan", frb_sea_scan, -1);

data/ext/isomorfeus_ferret_ext/frt_document.h

@@ -5,14 +5,11 @@
 #include "frt_doc_field.h"
 #include <ruby/encoding.h>
 
-/****************************************************************************
- *
- * FrtDocument
- *
- ****************************************************************************/
-
 #define FRT_DOC_INIT_CAPA 8
+
 typedef struct FrtDocument {
+    // frt_uchar ulid[16];
+    // char *ulid_c;
     FrtHash *field_dict;
     int field_count;
     int capa;

data/ext/isomorfeus_ferret_ext/frt_field_index.c

@@ -60,7 +60,7 @@ FrtFieldIndex *frt_field_index_get(FrtIndexReader *ir, ID field, const FrtFieldI
          * just use the field_infos field symbol */
         self->field = fi->name;
 
-        length = ir->max_doc(ir);
+        length = ir->max_doc_num(ir);
         if (length > 0) {
             FRT_TRY
             {