#include <strings.h>
Identifier for one of the character sets supported by CWB.
More...#define ATT_ALIGN (1<<2) |
Alignment attributes, ie a set of zones of alignment between a source and target corpus.
Referenced by aid_name(), cl_has_extended_alignment(), do_cqi_cl_alg2cpos(), do_cqi_cl_attribute_size(), do_cqi_cl_cpos2alg(), do_cqi_corpus_attributes(), get_alg_attribute(), interpreter(), main(), prepare_AlignmentConstraints(), printAlignedStrings(), show_basic_info(), show_position_values(), show_statistics(), update_context_descriptor(), and verify_context_descriptor().
#define ATT_ALL ATT_POS | ATT_STRUC | ATT_ALIGN | ATT_DYN |
shorthand for "all types of attribute"
#define ATT_DYN (1<<6) |
Dynamic attributes, ??
Referenced by aid_name(), attr_drop_attribute(), call_dynamic_attribute(), describe_attribute(), FunctionCall(), nr_of_arguments(), and show_position_values().
#define ATT_NONE 0 |
Referenced by aid_name(), att_hash_lookup(), attr_drop_attribute(), cqi_drop_attribute(), new_tabulation_item(), and print_tabulation().
#define ATT_POS (1<<0) |
Positional attributes, ie streams of word tokens, word tags - any "column" that has a value at every corpus position.
Referenced by add_key(), aid_name(), attr_drop_attribute(), collect_matches(), collect_matching_ids(), compose_kwic_line(), compute_grouping(), cumulative_id_frequency(), do_cqi_cl_attribute_size(), do_cqi_cl_cpos2id(), do_cqi_cl_cpos2str(), do_cqi_cl_id2cpos(), do_cqi_cl_id2freq(), do_cqi_cl_id2str(), do_cqi_cl_idlist2cpos(), do_cqi_cl_lexicon_size(), do_cqi_cl_regex2id(), do_cqi_cl_str2id(), do_cqi_corpus_attributes(), do_IDReference(), do_LabelReference(), do_show(), do_SimpleVariableReference(), do_StringConstraint(), evaluate_target(), get_attribute_size(), get_id_at_position(), get_id_frequency(), get_id_from_sortidx(), get_id_info(), get_id_of_string(), get_id_range(), get_id_string_len(), get_matched_corpus_positions(), get_positions(), get_sortidxpos_of_id(), get_string_at_position(), get_string_of_id(), interpreter(), inverted_file_is_compressed(), item_sequence_is_compressed(), main(), OpenPositionStream(), print_tabulation(), read_mapping(), red_factor(), Setop(), setup_attribute(), show_basic_info(), show_position_values(), show_statistics(), SortSubcorpus(), SystemCorpusSize(), update_context_descriptor(), and VerifyVariable().
#define ATT_REAL ATT_POS | ATT_STRUC | ATT_ALIGN |
shorthand for "all types of attribute except dynamic"
#define ATT_STRUC (1<<1) |
Structural attributes, ie a set of SGML/XML-ish "regions" in the corpus delimited by the same SGML/XML tag.
Referenced by add_key(), aid_name(), compute_grouping(), ComputePrintStructures(), do_attribute_show(), do_cqi_cl_attribute_size(), do_cqi_cl_cpos2lbound(), do_cqi_cl_cpos2rbound(), do_cqi_cl_cpos2struc(), do_cqi_cl_struc2cpos(), do_cqi_cl_struc2str(), do_cqi_corpus_attributes(), do_cqi_corpus_structural_attribute_has_values(), do_Description(), do_IDReference(), do_LabelReference(), do_StructuralContext(), do_XMLTag(), evaluate_target(), findcorpus(), get_bounds_of_nth_struc(), get_nr_of_strucs(), get_num_of_struc(), get_struc_attribute(), interpreter(), main(), print_tabulation(), setup_attribute(), show_basic_info(), show_position_values(), show_statistics(), structure_has_values(), structure_value(), update_context_descriptor(), and verify_context_descriptor().
#define ATTAT_FLOAT 5 |
Referenced by argid_name(), attat_name(), call_dynamic_attribute(), eval_bool(), get_leaf_value(), and makearg().
#define ATTAT_INT 3 |
Referenced by argid_name(), attat_name(), call_dynamic_attribute(), call_predefined_function(), eval_bool(), get_leaf_value(), and makearg().
#define ATTAT_NONE 0 |
Referenced by argid_name(), attat_name(), call_dynamic_attribute(), call_predefined_function(), eval_bool(), and get_leaf_value().
#define ATTAT_PAREF 6 |
Referenced by argid_name(), attat_name(), call_dynamic_attribute(), call_predefined_function(), eval_bool(), and get_leaf_value().
#define ATTAT_POS 1 |
Referenced by argid_name(), attat_name(), call_dynamic_attribute(), call_predefined_function(), eval_bool(), get_leaf_value(), makearg(), and setup_attribute().
#define ATTAT_STRING 2 |
Referenced by argid_name(), attat_name(), call_dynamic_attribute(), call_predefined_function(), eval_bool(), get_leaf_value(), and makearg().
#define ATTAT_VAR 4 |
Referenced by argid_name(), attat_name(), call_dynamic_attribute(), eval_bool(), makearg(), and nr_of_arguments().
#define CDA_EALIGN -9 |
no alignment at position
Referenced by cdperror_string(), cl_cpos2alg(), and get_extended_alignment().
#define CDA_EARGS -12 |
error in arguments for dynamic call
Referenced by call_dynamic_attribute(), and cdperror_string().
#define CDA_EATTTYPE -2 |
function was called on illegal attribute
Referenced by cdperror_string(), and send_cl_error().
#define CDA_EBADREGEX -16 |
bad regular expression
Referenced by cdperror_string(), cl_new_regex(), collect_matching_ids(), and send_cl_error().
#define CDA_EBUFFER -18 |
buffer overflow (hard-coded internal buffer sizes)
Referenced by cdperror_string(), and cl_set_intersection().
#define CDA_EFSETINV -17 |
invalid feature set format
Referenced by cdperror_string(), cl_make_set(), cl_set_intersection(), and cl_set_size().
#define CDA_EIDORNG -3 |
id out of range
Referenced by cdperror_string(), collect_matches(), get_id_string_len(), get_positions(), get_string_of_id(), OpenPositionStream(), and send_cl_error().
#define CDA_EIDXORNG -5 |
index out of range
Referenced by cdperror_string(), cl_alg2cpos(), get_bounds_of_nth_struc(), get_id_frequency(), get_id_from_sortidx(), send_cl_error(), and structure_value().
#define CDA_EINTERNAL -19 |
internal data consistency error (really bad)
Referenced by cdperror_string(), and structure_value().
#define CDA_ENODATA -11 |
can't load/create necessary data
Referenced by cdperror_string(), cl_alg2cpos(), cl_cpos2alg(), cl_max_alg(), collect_matches(), collect_matching_ids(), cumulative_id_frequency(), get_alg_attribute(), get_attribute_size(), get_bounds_of_nth_struc(), get_id_at_position(), get_id_frequency(), get_id_from_sortidx(), get_id_of_string(), get_id_range(), get_id_string_len(), get_nr_of_strucs(), get_num_of_struc(), get_positions(), get_sortidxpos_of_id(), get_string_of_id(), get_struc_attribute(), OpenPositionStream(), send_cl_error(), and structure_value().
#define CDA_ENOMEM -13 |
memory fault [unused]
Referenced by cdperror_string(), and send_cl_error().
#define CDA_ENOSTRING -6 |
no such string encoded
Referenced by cdperror_string(), and get_id_of_string().
#define CDA_ENULLATT -1 |
NULL passed as attribute argument.
Referenced by cdperror_string().
#define CDA_ENYI -15 |
not yet implemented
Referenced by cdperror_string(), get_sortidxpos_of_id(), and send_cl_error().
#define CDA_EOTHER -14 |
other error
Referenced by cdperror_string(), get_id_of_string(), get_id_string_len(), and send_cl_error().
#define CDA_EPATTERN -7 |
illegal pattern
Referenced by cdperror_string(), and send_cl_error().
#define CDA_EPOSORNG -4 |
position out of range
Referenced by cdperror_string(), cl_cpos2alg(), get_alg_attribute(), get_id_at_position(), get_leaf_value(), and send_cl_error().
#define CDA_EREMOTE -10 |
error in remote access
Referenced by cdperror_string().
#define CDA_ESTRUC -8 |
no structure at position
Referenced by cdperror_string(), cl_cpos2boundary(), get_num_of_struc(), and get_struc_attribute().
#define CDA_OK 0 |
everything fine; error values all less than 0
Referenced by call_dynamic_attribute(), call_predefined_function(), cdperror_string(), check_alignment_constraints(), cl_alg2cpos(), cl_cpos2alg(), cl_make_set(), cl_max_alg(), cl_new_regex(), cl_set_intersection(), cl_set_size(), collect_matches(), collect_matching_ids(), compress_reversed_index(), compute_code_lengths(), cumulative_id_frequency(), decode_check_huff(), decompress_check_reversed_index(), do_cqi_cl_regex2id(), do_show(), eval_bool(), get_alg_attribute(), get_attribute_size(), get_bounds_of_nth_struc(), get_corpus_positions(), get_id_at_position(), get_id_frequency(), get_id_from_sortidx(), get_id_info(), get_id_of_string(), get_id_range(), get_id_string_len(), get_leaf_value(), get_nr_of_strucs(), get_num_of_struc(), get_position_values(), get_positions(), get_sortidxpos_of_id(), get_string_at_position(), get_string_of_id(), get_struc_attribute(), map_token_to_class_number(), meet_mu(), member_of_class_s(), nr_of_arguments(), OpenPositionStream(), OptimizeStringConstraint(), print_info(), read_mapping(), send_cl_error(), Setop(), show_position_values(), structure_has_values(), and structure_value().
#define cl_cpos2id | ( | a, | |||
cpos | ) | get_id_at_position(a, cpos) |
#define cl_cpos2str | ( | a, | |||
cpos | ) | get_string_at_position(a, cpos) |
Referenced by do_cqi_cl_cpos2str(), print_tabulation(), show_position_values(), SortExternally(), and SortSubcorpus().
#define cl_cpos2struc2cpos | ( | a, | |||
cpos, | |||||
start, | |||||
end | ) | get_struc_attribute(a, cpos, start, end) |
Referenced by cl_cpos2boundary(), and show_position_values().
#define cl_cpos2struc2str | ( | a, | |||
cpos | ) | structure_value_at_position(a, cpos) |
Referenced by get_group_id(), and print_tabulation().
#define cl_delete_attribute | ( | a | ) | attr_drop_attribute(a) |
Referenced by cqi_drop_attribute().
#define cl_delete_corpus | ( | c | ) | drop_corpus(c) |
Referenced by main().
#define cl_delete_stream | ( | ps | ) | ClosePositionStream(ps) |
#define CL_DYN_STRING_SIZE 2048 |
maximum size of 'dynamic' strings
Referenced by call_predefined_function(), and cl_set_intersection().
#define cl_errno cderrno |
#define cl_error | ( | message | ) | cdperror(message) |
Referenced by main().
#define cl_error_string | ( | no | ) | cdperror_string(no) |
#define cl_free | ( | p | ) | do { if ((p) != NULL) { free(p); p = NULL; } } while (0) |
Safely frees memory.
p | Pointer to memory to be freed. |
Referenced by add_hosts_in_subnet_to_list(), addline(), after_Query(), assign_temp_to_sub(), attach_subcorpus(), attr_drop_attribute(), check_set(), cl_delete_int_list(), cl_delete_lexhash(), cl_delete_lexhash_entry(), cl_delete_regex(), cl_delete_string_list(), cl_free_string_list(), cl_lexhash_check_grow(), cl_make_set(), cl_new_regex(), close_range(), collect_matching_ids(), comp_drop_component(), creat_rev_corpus(), cwbci_check_line(), declare_range(), delete_interval(), delete_intervals(), DestroyAttributeList(), do_AddSubVariables(), do_cqi_cl_cpos2lbound(), do_cqi_cl_cpos2rbound(), do_cqi_cl_cpos2struc(), do_cqi_cqp_fdist_1(), do_cqi_cqp_fdist_2(), do_flagged_re_variable(), do_IDReference(), do_LabelReference(), do_SearchPattern(), do_StandardQuery(), do_undump(), do_XMLTag(), drop_corpus(), drop_mapping(), drop_single_mapping(), DropVariable(), evaltree2searchstr(), evaluate_target(), execute_side_effects(), expand_macro(), free_booltree(), free_environment(), free_group(), free_matchlist(), free_tabulation_list(), FreeIDList(), FreeSortClause(), get_fulllocalpath(), get_matched_corpus_positions(), get_positions(), initialize_cl(), load_macro_file(), MacroHashDelete(), main(), matchfirstpattern(), meet_mu(), open_input_stream(), open_range(), OptimizeStringConstraint(), parse_line(), print_tabulation(), RangeSetop(), RangeSort(), RecomputeAL(), RemoveNameFromAL(), scan_directory(), set_context_option_value(), set_corpus_matchlists(), set_target(), Setop(), setup_corpus(), SL_delete(), SortExternally(), SortSubcorpus(), SortSubcorpusRandomize(), split_subcorpus_spec(), Unchain(), validate_revcorp(), VariableDeleteItems(), VariableSubtractItem(), VerifyList(), and VerifyVariable().
#define cl_id2all | ( | a, | |||
sid, | |||||
freq, | |||||
len | ) | get_id_info(a, sid, freq, len) |
#define cl_id2cpos | ( | a, | |||
id, | |||||
freq | ) | get_positions(a, id, freq, NULL, 0) |
Referenced by do_cqi_cl_id2cpos().
#define cl_id2freq | ( | a, | |||
id | ) | get_id_frequency(a, id) |
#define cl_id2sort | ( | a, | |||
id | ) | get_sortidxpos_of_id(a, id) |
#define cl_id2str | ( | a, | |||
id | ) | get_string_of_id(a, id) |
Referenced by add_key(), create_feature_maps(), do_cqi_cl_id2str(), Group_id2str(), i2compare(), and main().
#define cl_id2strlen | ( | a, | |||
id | ) | get_id_string_len(a, id) |
Referenced by create_feature_maps().
#define cl_idlist2cpos | ( | a, | |||
idlist, | |||||
idlist_size, | |||||
sort, | |||||
size | ) | collect_matches(a, idlist, idlist_size, sort, size, NULL, 0) |
Referenced by do_cqi_cl_idlist2cpos().
#define cl_idlist2freq | ( | a, | |||
list, | |||||
size | ) | cumulative_id_frequency(a, list, size) |
Referenced by OptimizeStringConstraint().
#define cl_index_compressed | ( | a | ) | inverted_file_is_compressed(a) |
#define cl_max_cpos | ( | a | ) | get_attribute_size(a) |
#define cl_max_id | ( | a | ) | get_id_range(a) |
#define cl_new_attribute | ( | c, | |||
name, | |||||
type | ) | find_attribute(c, name, type, NULL) |
Referenced by add_key(), cqi_lookup_attribute(), do_show(), do_XMLTag(), main(), print_tabulation(), and show_basic_info().
#define cl_new_corpus | ( | reg, | |||
name | ) | setup_corpus(reg, name) |
Referenced by main(), and parse_options().
#define cl_new_stream | ( | a, | |||
id | ) | OpenPositionStream(a, id) |
#define cl_regex2id | ( | a, | |||
re, | |||||
flags, | |||||
size | ) | collect_matching_ids(a, re, flags, size) |
Referenced by add_key(), do_cqi_cl_regex2id(), and do_show().
#define cl_sequence_compressed | ( | a | ) | item_sequence_is_compressed(a) |
#define cl_sort2id | ( | a, | |||
sid | ) | get_id_from_sortidx(a, sid) |
#define cl_standard_registry | ( | ) | central_corpus_directory() |
Referenced by find_corpus(), and main().
#define cl_str2id | ( | a, | |||
str | ) | get_id_of_string(a, str) |
Referenced by create_feature_maps(), do_cqi_cl_str2id(), and do_show().
#define cl_struc2cpos | ( | a, | |||
struc, | |||||
start, | |||||
end | ) | get_bounds_of_nth_struc(a, struc, start, end) |
#define cl_struc2str | ( | a, | |||
struc | ) | structure_value(a, struc) |
#define cl_struc_values | ( | a | ) | structure_has_values(a) |
#define IGNORE_CASE 1 |
Flag ignore-case in regular expression matching.
Referenced by add_key(), cl_new_regex(), cl_string_maptable(), collect_matching_ids(), main(), print_pattern(), and setup_corpus().
#define IGNORE_DIAC 2 |
Flag ignore-diacritics in regular expression matching.
Referenced by add_key(), cl_new_regex(), cl_string_maptable(), collect_matching_ids(), main(), and print_pattern().
#define IGNORE_REGEX 4 |
Flag for: don't use regular expression matching - match as a literal string.
Not used in the CL but in use in CQP.
Referenced by do_flagged_re_variable(), do_flagged_string(), do_mval_string(), do_XMLTag(), and print_pattern().
#define STRUC_INSIDE 1 |
cl_cpos2boundary() return flag: specified position is WITHIN a region of this s-attribute
Referenced by cl_cpos2boundary().
#define STRUC_LBOUND 2 |
cl_cpos2boundary() return flag: specified position is AT THE START BOUNDARY OF a region of this s-attribute
Referenced by cl_cpos2boundary().
#define STRUC_RBOUND 4 |
cl_cpos2boundary() return flag: specified position is AT THE END BOUNDARY OF a region of this s-attribute
Referenced by cl_cpos2boundary().
typedef union _Attribute Attribute |
The Attribute object: an entire segment of a corpus (of any flavour; s, p etc).
typedef struct _CL_BitVec* CL_BitVec |
The CL_BitVec object: doesn't seem to exist {???-- AH}.
typedef struct _cl_int_list* cl_int_list |
automatically growing list of integers (just what you always need .
..)
typedef struct _cl_lexhash* cl_lexhash |
The cl_lexhash class (lexicon hashes, with IDs and frequency counts).
A "lexicon hash" links strings to integers. Each cl_lexhash object represents an entire table of such things; individual string-to-int links are represented by cl_lexhash_entry objects.
Within the cl_lexhash, the entries are grouped into buckets. A bucket is the term for a "slot" on the hash table. The linked-list in a given bucket represent all the different string-keys that map to one particular index value.
Each entry contains the key itself (for search-and-retrieval), the frequency of that type (incremented when a token is added that is already in the lexhash), an ID integer, plus a bundle of "data" associated with that string.
These lexicon hashes are used, notably, in the encoding of corpora to CWB-index-format.
typedef struct _cl_lexhash_entry * cl_lexhash_entry |
Underlying structure for the cl_lexhash_entry class.
typedef struct _cl_string_list* cl_string_list |
automatically growing list of strings (just what you always need .
..)
typedef enum ECorpusCharset CorpusCharset |
Identifier for one of the character sets supported by CWB.
typedef struct TCorpusProperty * CorpusProperty |
The CorpusProperty object.
The underlying structure takes the form of a linked-list entry.
Each Corpus object has, as one of its members, the head entry on a list of CorpusProperties.
typedef struct _DCR DynCallResult |
The DynCallResult object (needed to allocate space for dynamic function arguments).
typedef struct _position_stream_rec_* PositionStream |
The PositionStream object: gives stream-like reading of an Attribute.
enum ECorpusCharset |
int attr_drop_attribute | ( | Attribute * | attribute | ) |
Deletes the specified Attribute object.
References _Attribute::any, Dynamic_Attribute::arglist, ATT_DYN, ATT_NONE, ATT_POS, TCorpus::attributes, Dynamic_Attribute::call, cl_free, comp_drop_component(), CompDirectory, CompLast, corpus, _Attribute::dyn, POS_Attribute::hc, _DynArg::next, _Attribute::pos, and _Attribute::type.
Referenced by drop_attribute(), and drop_corpus().
int call_dynamic_attribute | ( | Attribute * | attribute, | |
DynCallResult * | dcr, | |||
DynCallResult * | args, | |||
int | nr_args | |||
) |
Calls a dynamic attribute.
This is the attribute access function for dynamic attributes.
attribute | The (dynamic) attribute in question. | |
dcr | Location for the result (*int or *char). | |
args | Location of the parameters (of *int or *char). | |
nr_args | Number of parameters. |
References Dynamic_Attribute::arglist, ATT_DYN, ATTAT_FLOAT, ATTAT_INT, ATTAT_NONE, ATTAT_PAREF, ATTAT_POS, ATTAT_STRING, ATTAT_VAR, Dynamic_Attribute::call, CDA_EARGS, CDA_OK, cderrno, _DCR::charres, check_arg, cl_strdup(), _Attribute::dyn, error(), _DCR::floatres, _DCR::intres, _DynArg::next, Dynamic_Attribute::res_type, _DCR::type, _DynArg::type, and _DCR::value.
Referenced by get_leaf_value().
void cdperror | ( | char * | message | ) |
Prints an error message, together with a string identifying the current error number.
References cderrno, and cdperror_string().
Referenced by compress_reversed_index(), compute_code_lengths(), decompress_check_reversed_index(), do_show(), print_info(), and show_position_values().
char* cdperror_string | ( | int | errno | ) |
Gets a string describing the error identified by an error number.
errno | Error number integer (a CDA_* constant as defined in cl.h) |
References CDA_EALIGN, CDA_EARGS, CDA_EATTTYPE, CDA_EBADREGEX, CDA_EBUFFER, CDA_EFSETINV, CDA_EIDORNG, CDA_EIDXORNG, CDA_EINTERNAL, CDA_ENODATA, CDA_ENOMEM, CDA_ENOSTRING, CDA_ENULLATT, CDA_ENYI, CDA_EOTHER, CDA_EPATTERN, CDA_EPOSORNG, CDA_EREMOTE, CDA_ESTRUC, and CDA_OK.
Referenced by cdperror(), ensure_corpus_size(), and OptimizeStringConstraint().
char* central_corpus_directory | ( | ) |
Gets a string containing the path of the default registry directory.
References regdir, REGISTRY_DEFAULT_PATH, and REGISTRY_ENVVAR.
Referenced by load_corpusnames(), main(), and setup_corpus().
int cl_alg2cpos | ( | Attribute * | attribute, | |
int | alg, | |||
int * | source_region_start, | |||
int * | source_region_end, | |||
int * | target_region_start, | |||
int * | target_region_end | |||
) |
Gets the corpus positions of an alignment on the given align-attribute.
Note that four corpus positions are retrieved, into the addresses given as parameters.
attribute | The align-attribute to look on. | |
alg | The ID of the alignment whose positions are wanted. | |
source_region_start | Location to put source corpus start position. | |
source_region_end | Location to put source corpus end position. | |
target_region_start | Location to put target corpus start position. | |
target_region_end | Location to put target corpus end position. |
References CDA_EIDXORNG, CDA_ENODATA, CDA_OK, cderrno, cl_has_extended_alignment(), CompAlignData, CompXAlignData, TMblob::data, TComponent::data, ensure_component(), and TComponent::size.
Referenced by check_alignment_constraints(), compose_kwic_line(), do_cqi_cl_alg2cpos(), printAlignedStrings(), and show_position_values().
void* cl_calloc | ( | size_t | nr_of_elements, | |
size_t | element_size | |||
) |
safely allocates memory calloc-style.
nr_of_elements | Number of elements to allocate | |
element_size | Size of each element |
Referenced by alloc_mblob(), cl_new_int_list(), cl_new_lexhash(), cl_new_string_list(), collect_matching_ids(), compute_code_lengths(), declare_range(), evaluate_target(), main(), and validate_revcorp().
CorpusCharset cl_charset_from_name | ( | char * | name | ) |
Gets a CorpusCharset enumeration with the id code for the given string.
References _charset_spec::name, and unknown_charset.
Referenced by add_corpus_property(), and cwbci_parse_options().
char* cl_charset_name | ( | CorpusCharset | id | ) |
Gets a string containing the name of the specified CorpusCharset character set object.
Note that returned string cannot be modified.
References _charset_spec::name.
Referenced by corpus_info().
char* cl_charset_name_canonical | ( | char * | name_to_check | ) |
Checks whether a string represents a valid charset, and returns a pointer to the name in canonical form (ie lacking any non-standard case there may be in the input string).
name_to_check | String containing the character set name to be checked |
References _charset_spec::name.
Referenced by cwbci_parse_options(), and parse_options().
CorpusCharset cl_corpus_charset | ( | Corpus * | corpus | ) |
Retrieves the special 'charset' property.
corpus | The corpus object from which to retrieve the charset |
References TCorpus::charset.
Referenced by add_key(), and print_xml_declaration().
char* cl_corpus_property | ( | Corpus * | corpus, | |
char * | property | |||
) |
Gets the value of the specified corpus property.
corpus | Pointer to the Corpus object. | |
property | Name of the property to retrieve. |
References cl_first_corpus_property(), cl_next_corpus_property(), TCorpusProperty::property, and TCorpusProperty::value.
Referenced by add_corpus_property(), and corpus_info().
int cl_cpos2alg | ( | Attribute * | attribute, | |
int | cpos | |||
) |
Gets the id number of the alignment at the specified corpus position.
attribute | The align-attribute to look on. | |
cpos | The corpus position to look at. |
References CDA_EALIGN, CDA_ENODATA, CDA_EPOSORNG, CDA_OK, cderrno, cl_has_extended_alignment(), CompAlignData, CompXAlignData, TMblob::data, TComponent::data, ensure_component(), get_alignment(), get_extended_alignment(), and TComponent::size.
Referenced by check_alignment_constraints(), compose_kwic_line(), do_cqi_cl_cpos2alg(), printAlignedStrings(), and show_position_values().
int cl_cpos2boundary | ( | Attribute * | a, | |
int | cpos | |||
) |
Compares the location of a corpus position to the regions of an s-attribute.
This determines whether the specified corpus position is within a region (i.e. a structure, an instance of that s-attribute) on the given s-attribute; and/or on a boundary; or outside a region.
a | The s-attribute on which to search. | |
cpos | The corpus position to look for. |
References CDA_ESTRUC, cderrno, cl_cpos2struc2cpos, STRUC_INSIDE, STRUC_LBOUND, and STRUC_RBOUND.
int cl_cpos2struc | ( | Attribute * | a, | |
int | cpos | |||
) |
Gets the ID number of a structure (instance of an s-attribute) that is found at the given corpus position.
a | The s-attribute on which to search. | |
cpos | The corpus position to look for. |
References cderrno, and get_num_of_struc().
Referenced by compose_kwic_line(), do_cqi_cl_cpos2lbound(), do_cqi_cl_cpos2rbound(), do_cqi_cl_cpos2struc(), eval_constraint(), get_position_values(), main(), show_position_values(), and showSurroundingStructureValues().
void cl_delete_int_list | ( | cl_int_list | l | ) |
Deletes a cl_int_list object.
References cl_free, and _cl_int_list::data.
void cl_delete_lexhash | ( | cl_lexhash | hash | ) |
Deletes a cl_lexhash object.
This deletes all the entries in all the buckets in the lexhash, plus the cl_lexhash itself.
hash | The cl_lexhash to delete. |
References _cl_lexhash::buckets, cl_delete_lexhash_entry(), cl_free, _cl_lexhash_entry::next, and _cl_lexhash::table.
Referenced by main().
void cl_delete_regex | ( | CL_Regex | rx | ) |
Deletes a CL_Regex object.
rx | The CL_Regex to delete. |
References _CL_Regex::buffer, cl_free, _CL_Regex::grain, _CL_Regex::grains, and _CL_Regex::iso_string.
Referenced by collect_matching_ids(), free_booltree(), and free_environment().
void cl_delete_string_list | ( | cl_string_list | l | ) |
Deletes a cl_string_list object.
References cl_free, and _cl_string_list::data.
Referenced by cl_make_set(), main(), and parse_options().
CorpusProperty cl_first_corpus_property | ( | Corpus * | corpus | ) |
Gets the first entry in this corpus's list of properties.
(The corpus properties iterator / property datatype is public.)
corpus | Pointer to the Corpus object. |
References TCorpus::properties.
Referenced by cl_corpus_property(), and corpus_info().
void cl_free_string_list | ( | cl_string_list | l | ) |
Frees all the strings in the cl_string_list object.
References cl_free, _cl_string_list::data, and _cl_string_list::size.
Referenced by main().
void cl_get_rng_state | ( | unsigned int * | i1, | |
unsigned int * | i2 | |||
) |
Reads current state of CL-internal random number generator.
The integers currently held in RNG_I1 and RNG_I2 are written to the two memory locations supplied as arguments.
i1 | Target location for the value of RNG_I1 | |
i2 | Target location for the value of RNG_I2 |
int cl_has_extended_alignment | ( | Attribute * | attribute | ) |
Checks whether an attribute's XALIGN component exists, that is, whether or not it has extended alignment.
attribute | An align-attribute. |
References ATT_ALIGN, cderrno, check_arg, component_state(), ComponentLoaded, ComponentUnloaded, and CompXAlignData.
Referenced by cl_alg2cpos(), cl_cpos2alg(), cl_max_alg(), and show_statistics().
void cl_int_list_append | ( | cl_int_list | l, | |
int | val | |||
) |
Appends an integer to the end of a cl_int_list object.
References cl_int_list_set(), and _cl_int_list::size.
int cl_int_list_get | ( | cl_int_list | l, | |
int | n | |||
) |
Retrieves an element from a cl_int_list object.
l | The list to search. | |
n | The element to retrieve. |
References _cl_int_list::data, and _cl_int_list::size.
void cl_int_list_lumpsize | ( | cl_int_list | l, | |
int | s | |||
) |
Sets the lumpsize of a cl_int_list object.
l | The cl_int_list. | |
s | The new lumpsize. |
References _cl_int_list::lumpsize, and LUMPSIZE.
void cl_int_list_qsort | ( | cl_int_list | l | ) |
Sorts a cl_int_list object.
The list of integers are sorted into ascending order.
References cl_int_list_intcmp(), _cl_int_list::data, and _cl_int_list::size.
void cl_int_list_set | ( | cl_int_list | l, | |
int | n, | |||
int | val | |||
) |
Sets an integer on a cl_int_list object.
The n'th element on the list is set to val, and the list is auto-extended if necessary.
References _cl_int_list::allocated, cl_realloc(), _cl_int_list::data, _cl_int_list::lumpsize, and _cl_int_list::size.
Referenced by cl_int_list_append().
int cl_int_list_size | ( | cl_int_list | l | ) |
Gets the current size of a cl_int_list object (number of elements on the list).
References _cl_int_list::size.
cl_lexhash_entry cl_lexhash_add | ( | cl_lexhash | hash, | |
char * | token | |||
) |
Adds a token to a cl_lexhash table.
If the string is already in the hash, its frequency count is increased by 1.
Otherwise, a new entry is created, with an auto-assigned ID; note that the string is duplicated, so the original string that is passed to this function does not need ot be kept in memory.
hash | The hash table to add to. | |
token | The string to add. |
References cl_lexhash_find_i(), cl_malloc(), cl_strdup(), _cl_lexhash_entry::data, _cl_lexhash::entries, _cl_lexhash_entry::freq, _cl_lexhash_entry::id, _cl_lexhash_entry_data::integer, _cl_lexhash_entry::key, _cl_lexhash_entry::next, _cl_lexhash::next_id, _cl_lexhash_entry_data::numeric, _cl_lexhash_entry_data::pointer, and _cl_lexhash::table.
Referenced by addline(), close_range(), declare_range(), main(), open_range(), and write_region_to_disk().
void cl_lexhash_auto_grow | ( | cl_lexhash | hash, | |
int | flag | |||
) |
Turns a cl_lexhash's ability to autogrow on or off.
When this setting is switched on, the lexhash will grow automatically to avoid performance degradation.
Note the default value for this setting is SWITCHED ON.
hash | The hash that will be affected. | |
flag | New value for autogrow setting: boolean where true is on and false is off. |
References _cl_lexhash::auto_grow.
int cl_lexhash_del | ( | cl_lexhash | hash, | |
char * | token | |||
) |
Deletes a string from a hash.
The entry corresponding to the specified string is removed from the lexhash. If the string is not in the lexhash to begin with, no action is taken.
hash | The hash to alter. | |
token | The string to remove. |
References cl_delete_lexhash_entry(), cl_lexhash_find_i(), _cl_lexhash::entries, _cl_lexhash_entry::freq, _cl_lexhash_entry::next, and _cl_lexhash::table.
cl_lexhash_entry cl_lexhash_find | ( | cl_lexhash | hash, | |
char * | token | |||
) |
Finds the entry corresponding to a particular string within a cl_lexhash.
hash | The hash to search. | |
token | The key-string to look for. |
References cl_lexhash_find_i().
Referenced by close_range(), main(), open_range(), print_range_registry_line(), and write_region_to_disk().
int cl_lexhash_freq | ( | cl_lexhash | hash, | |
char * | token | |||
) |
Gets the frequency of a particular string within a lexhash.
hash | The hash to look in. | |
token | The string to look for. |
References cl_lexhash_find_i(), and _cl_lexhash_entry::freq.
Referenced by main(), and open_range().
int cl_lexhash_id | ( | cl_lexhash | hash, | |
char * | token | |||
) |
Gets the ID of a particular string within a lexhash.
Note this is the ID integer that identifies THAT PARTICULAR STRING, not the hash value of that string - which only identifies the bucket the string is found in!
hash | The hash to look in. | |
token | The string to look for. |
References cl_lexhash_find_i(), and _cl_lexhash_entry::id.
Referenced by addline(), and declare_range().
void cl_lexhash_set_cleanup_function | ( | cl_lexhash | lh, | |
void(*)(cl_lexhash_entry) | func | |||
) |
int cl_lexhash_size | ( | cl_lexhash | hash | ) |
Gets the number of different strings stored in a lexhash.
This returns the total number of entries in all the bucket linked-lists in the whole hashtable.
hash | The hash to size up. |
References _cl_lexhash::buckets, _cl_lexhash_entry::next, and _cl_lexhash::table.
char* cl_make_set | ( | char * | s, | |
int | split | |||
) |
Generates a set attribute value.
s | The input string. | |
split | Boolean; if True, s is split on whitespace. If False, the function expects input in '|'-delimited format. |
References CDA_EFSETINV, CDA_OK, cderrno, cl_delete_string_list(), cl_free, cl_malloc(), cl_new_string_list(), cl_strdup(), cl_string_list_append(), cl_string_list_get(), cl_string_list_qsort(), and cl_string_list_size().
Referenced by addline(), check_set(), and open_range().
void* cl_malloc | ( | size_t | bytes | ) |
safely allocates memory malloc-style.
This function allocates a block of memory of the requested size, and does a test for malloc() failure which aborts the program and prints an error message if the system is out of memory. So the return value of this function can be used without further testing for malloc() failure.
bytes | Number of bytes to allocate |
Referenced by accessible(), add_corpus_property(), add_grant_to_last_user(), add_host_to_list(), add_hosts_in_subnet_to_list(), add_tabular_pattern(), add_to_string(), add_user_to_list(), AddNameToAL(), alloc_mblob(), Allocate(), attach_subcorpus(), binsert_g(), check_alignment_constraints(), cl_lexhash_add(), cl_make_set(), cl_new_int_list(), cl_new_lexhash(), cl_new_regex(), cl_new_string_list(), cl_string_latex2iso(), collect_matches(), collect_matching_ids(), combine_subcorpus_spec(), compute_code_lengths(), compute_grouping(), ComputeGroupExternally(), cqi_read_bool_list(), cqi_read_byte_list(), cqi_read_int_list(), cqi_read_string(), cqi_read_string_list(), cqp_run_mu_query(), cqp_run_tab_query(), creat_rev_corpus(), creat_rev_corpus_idx(), create_bitfield(), define_macro(), do_cqi_cqp_query(), do_flagged_re_variable(), do_MeetStatement(), do_mval_string(), do_undump(), do_UnionStatement(), do_XMLTag(), duplicate_corpus(), evaltree2searchstr(), find_corpus_registry(), get_leaf_value(), get_matched_corpus_positions(), get_positions(), GetVariableItems(), GetVariableStrings(), hash_add(), labellookup(), list_macros(), macro_iterator_next_prototype(), MacroAddSegment(), MacroHashAdd(), main(), make_attribute_hash(), make_first_tabular_pattern(), make_temp_corpus(), MakeMacroHash(), mallocfile(), matchfirstpattern(), meet_mu(), mval_string_conversion(), new_reftab(), new_symbol_table(), new_tabulation_item(), NewAttributeList(), NewContextDescriptor(), NewVariable(), open_input_stream(), OptimizeStringConstraint(), parse_macro_name(), PushInputBuffer(), quote_file_path(), RangeSetop(), RangeSort(), read_mapping(), ReadHCD(), scan_directory(), set_corpus_matchlists(), set_target(), Setop(), show_corpora_files1(), simulate_dfa(), SL_insert_after_point(), SortExternally(), SortSubcorpus(), SortSubcorpusRandomize(), strdupto(), try_optimization(), and VariableAddItem().
int cl_max_alg | ( | Attribute * | attribute | ) |
Gets the id number of alignments on this align-attribute.
This is equal to the maximum alignment on this attribute.
attribute | An align-attribute. |
References CDA_ENODATA, CDA_OK, cderrno, cl_has_extended_alignment(), CompAlignData, CompXAlignData, ensure_component(), and TComponent::size.
Referenced by do_cqi_cl_attribute_size(), and show_statistics().
int cl_max_struc | ( | Attribute * | a | ) |
Gets the maximum for this S-attribute (ie the size of the S-attribute).
The result of this function is equal to the number of instances of this s-attribute in the corpus.
The s-attribute to evaluate.
References cderrno, and get_nr_of_strucs().
Referenced by add_key(), compose_kwic_line(), do_cqi_cl_attribute_size(), main(), matchfirstpattern(), and show_statistics().
cl_int_list cl_new_int_list | ( | void | ) |
Creates a new cl_int_list object.
References _cl_int_list::allocated, cl_calloc(), cl_malloc(), _cl_int_list::data, _cl_int_list::lumpsize, LUMPSIZE, and _cl_int_list::size.
cl_lexhash cl_new_lexhash | ( | int | buckets | ) |
Creates a new cl_lexhash object.
buckets | The number of buckets in the newly-created cl_lexhash; set to 0 to use the default number of buckets. |
References _cl_lexhash::auto_grow, _cl_lexhash::buckets, cl_calloc(), cl_malloc(), _cl_lexhash::cleanup_func, _cl_lexhash::comparisons, DEFAULT_NR_OF_BUCKETS, _cl_lexhash::entries, find_prime(), _cl_lexhash::last_performance, _cl_lexhash::next_id, PERFORMANCE_COUNT, _cl_lexhash::performance_counter, and _cl_lexhash::table.
Referenced by cl_lexhash_check_grow(), declare_range(), declare_wattr(), main(), and write_region_to_disk().
CL_Regex cl_new_regex | ( | char * | regex, | |
int | flags, | |||
CorpusCharset | charset | |||
) |
Create a new CL_regex object (ie a regular expression buffer).
The regular expression is preprocessed according to the flags, and anchored to the start and end of the string. (That is, ^ is added to the start, $ to the end.)
Then the resulting regex is compiled (using POSIX compilation) and optimised. Currently the character set parameter is ignored and assumed to be Latin-1.
regex | String containing the regular expression | |
flags | IGNORE_CASE, or IGNORE_DIAC, or both, or 0. | |
charset | The character set of the regex. Currently ignored. |
References _CL_Regex::anchor_end, _CL_Regex::anchor_start, _CL_Regex::buffer, CDA_EBADREGEX, CDA_OK, cderrno, _CL_Regex::charset, cl_debug, cl_free, cl_malloc(), cl_regex_error, cl_regopt_analyse(), cl_regopt_anchor_end, cl_regopt_anchor_start, cl_regopt_grain, cl_regopt_grain_len, cl_regopt_grains, cl_regopt_jumptable, cl_strdup(), cl_string_canonical(), cl_string_latex2iso(), _CL_Regex::flags, _CL_Regex::grain, _CL_Regex::grain_len, _CL_Regex::grains, IGNORE_CASE, IGNORE_DIAC, _CL_Regex::iso_string, _CL_Regex::jumptable, and MAX_LINE_LENGTH.
Referenced by add_key(), collect_matching_ids(), do_flagged_string(), and do_XMLTag().
cl_string_list cl_new_string_list | ( | void | ) |
Creates a new cl_string_list object.
References _cl_string_list::allocated, cl_calloc(), cl_malloc(), _cl_string_list::data, _cl_string_list::lumpsize, LUMPSIZE, and _cl_string_list::size.
Referenced by cl_make_set(), cwbci_parse_options(), declare_range(), main(), and scan_directory().
CorpusProperty cl_next_corpus_property | ( | CorpusProperty | prop | ) |
Gets the next corpus property on the list of properties.
(The corpus properties iterator / property datatype is public.)
prop | The current property. |
References TCorpusProperty::next.
Referenced by cl_corpus_property(), and corpus_info().
unsigned int cl_random | ( | void | ) |
Gets a random number.
Part of the CL-internal random number generator.
References RNG_I1, and RNG_I2.
Referenced by cl_runif(), and SortSubcorpusRandomize().
void cl_randomize | ( | void | ) |
Initialises the CL-internal random number generator from the current system time.
References cl_set_seed().
Referenced by cqp_randomize(), initialize_cqp(), and main().
void* cl_realloc | ( | void * | block, | |
size_t | bytes | |||
) |
safely reallocates memory.
block | Pointer to the block to be reallocated | |
bytes | Number of bytes to allocate to the resized memory block @ return Pointer to the block of reallocated memory |
Referenced by add_to_string(), binsert_g(), cl_int_list_set(), cl_string_list_set(), ComputeGroupExternally(), ComputeGroupInternally(), get_positions(), load_macro_file(), meet_mu(), NewVariable(), RangeSetop(), read_mapping(), Reallocate(), Setop(), and VariableAddItem().
int cl_regex_match | ( | CL_Regex | rx, | |
char * | str | |||
) |
Matches a regular expression against a string.
The regular expression contained in the CL_Regex is compared to the string. No settings or flags are passed to this function; rather, the settings that rx was created with are used.
rx | The regular expression to match. | |
str | The string to compare the regex to. |
References _CL_Regex::anchor_end, _CL_Regex::anchor_start, _CL_Regex::buffer, cl_string_canonical(), _CL_Regex::flags, _CL_Regex::grain, _CL_Regex::grain_len, _CL_Regex::grains, _CL_Regex::iso_string, and _CL_Regex::jumptable.
Referenced by eval_bool(), eval_constraint(), main(), and matchfirstpattern().
int cl_regex_optimised | ( | CL_Regex | rx | ) |
Finds the level of optimisation of a CL_Regex.
This function returns the approximate level of optimisation, computed from the ratio of grain length to number of grains (0 = no grains, ergo not optimised at all).
rx | The CL_Regex to check. |
References _CL_Regex::grain_len, and _CL_Regex::grains.
Referenced by collect_matching_ids().
double cl_runif | ( | void | ) |
Gets a random number in the range [0,1] with uniform distribution.
Part of the CL-internal random number generator.
References cl_random().
Referenced by do_cqi_cqp_query(), and do_reduce().
void cl_set_debug_level | ( | int | level | ) |
Sets the debug level configuration variable.
References cl_debug.
Referenced by execute_side_effects(), main(), parse_options(), and set_default_option_values().
int cl_set_intersection | ( | char * | result, | |
const char * | s1, | |||
const char * | s2 | |||
) |
Computes the intersection of two set attribute values.
Compute intersection of two set attribute values (in standard syntax, i.e. sorted and '|'-delimited); memory for the result string must be allocated by the caller.
References CDA_EBUFFER, CDA_EFSETINV, CDA_OK, cderrno, CL_DYN_STRING_SIZE, and cl_strcmp().
Referenced by call_predefined_function().
void cl_set_memory_limit | ( | int | limit | ) |
Sets the memory limit.
NOTE name of parameter differs here and in cl.h -- TODO
References cl_memory_limit.
Referenced by main().
void cl_set_optimize | ( | int | state | ) |
Turns optimization on or off.
state | Boolean (true turns it on, false turns it off). |
References cl_optimize.
Referenced by execute_side_effects(), main(), and set_default_option_values().
void cl_set_rng_state | ( | unsigned int | i1, | |
unsigned int | i2 | |||
) |
Restores the state of the CL-internal random number generator.
i1 | The value to set the first RNG integer to (if zero, resets it to 1) | |
i2 | The value to set the second RNG integer to (if zero, resets it to 1) |
References RNG_I1, and RNG_I2.
Referenced by cl_set_seed(), and SortSubcorpusRandomize().
void cl_set_seed | ( | unsigned int | seed | ) |
Initialises the CL-internal random number generator.
seed | A single 32bit number to use as the seed |
References cl_set_rng_state().
Referenced by cl_randomize().
int cl_set_size | ( | char * | s | ) |
Counts the number of elements in a set attribute value.
This function counts the number of elements in a set attribute value (using '|'-delimited standard syntax);
References CDA_EFSETINV, CDA_OK, and cderrno.
Referenced by call_predefined_function().
int cl_strcmp | ( | char * | s1, | |
char * | s2 | |||
) |
CL internal string comparison (uses signed char on all platforms).
Referenced by cl_set_intersection(), cl_string_list_strcmp(), get_id_of_string(), and scompare().
char* cl_strdup | ( | char * | string | ) |
safely duplicates a string.
string | Pointer to the original string |
Referenced by add_grant_to_last_user(), add_user_to_list(), addline(), AddNameToAL(), after_Query(), assign_temp_to_sub(), att_hash_lookup(), attach_subcorpus(), call_dynamic_attribute(), changecase_string(), cl_lexhash_add(), cl_make_set(), cl_new_regex(), close_range(), combine_subcorpus_spec(), component_full_name(), compose_kwic_line(), cwbci_check_line(), cwbci_parse_options(), declare_range(), declare_wattr(), do_XMLTag(), duplicate_corpus(), evaltree2searchstr(), execute_side_effects(), expand_filename(), expand_macro(), get_fulllocalpath(), GetSystemCorpus(), labellookup(), load_corpusnames(), load_macro_file(), MacroHashAdd(), main(), make_temp_corpus(), NewVariable(), open_pager(), open_range(), open_stream(), parse_line(), parse_options(), print_tabulation(), printAlignedStrings(), quote_file_path(), read_mapping(), set_context_option_value(), set_default_option_values(), setup_corpus(), SL_insert_after_point(), SortSubcorpus(), split_attribute_spec(), split_subcorpus_spec(), VariableAddItem(), and VerifyVariable().
void cl_string_canonical | ( | char * | s, | |
int | flags | |||
) |
Converts a string to canonical form.
The "canonical form" of a string is for use in comparisons where case-insensitivity and/or diacritic insensitivity is desired.
Note that the string s is modified in place.
s | The string (must be Latin-1!) | |
flags | The flags that specify which conversions are required. Can be IGNORE_CASE and/or IGNORE_DIAC. |
References cl_string_maptable(), and latin1.
Referenced by cl_new_regex(), cl_regex_match(), collect_matching_ids(), main(), print_tabulation(), setup_corpus(), and SortSubcorpus().
char* cl_string_latex2iso | ( | char * | str, | |
char * | result, | |||
int | target_len | |||
) |
Converts strings with latex-style blackslash escapes for accented characters to ISO-8859-1 (Latin-1).
Syntax:
\[AaOoUus..] --> corresponding ISO 8859-1 character
octal} --> ISO 8859-1 character
str | The string to convert. | |
result | The location to put the altered string (which should be shorter, or at least no longer than, the input string. If this parameter is NULL, space is automatically allocated for the output. result is allowed to be the same as str. | |
target_len | The maximum length of the target string. If result is NULL, then this is set automatically. |
References cl_malloc(), popc, and pushc.
Referenced by cl_new_regex(), do_flagged_string(), do_SetVariableValue(), and do_XMLTag().
void cl_string_list_append | ( | cl_string_list | l, | |
char * | val | |||
) |
Appends a string pointer to the end of a cl_string_list object.
References cl_string_list_set(), and _cl_string_list::size.
Referenced by cl_make_set(), cwbci_check_line(), declare_range(), parse_options(), and scan_directory().
char* cl_string_list_get | ( | cl_string_list | l, | |
int | n | |||
) |
Retrieves an element from a cl_string_list object.
l | The list to search. | |
n | The element to retrieve. |
References _cl_string_list::data, and _cl_string_list::size.
Referenced by cl_make_set(), close_range(), cwbci_check_line(), get_input_line(), main(), open_range(), parse_options(), and print_range_registry_line().
void cl_string_list_lumpsize | ( | cl_string_list | l, | |
int | s | |||
) |
Sets the lumpsize of a cl_string_list object.
l | The cl_string_list. | |
s | The new lumpsize. |
References _cl_string_list::lumpsize, and LUMPSIZE.
void cl_string_list_qsort | ( | cl_string_list | l | ) |
Sorts a cl_string_list object.
The list of strings is sorted using cl_strcmp().
References cl_string_list_strcmp(), _cl_string_list::data, and _cl_string_list::size.
Referenced by cl_make_set(), and scan_directory().
void cl_string_list_set | ( | cl_string_list | l, | |
int | n, | |||
char * | val | |||
) |
Sets a string pointer on a cl_string_list object.
The n'th element on the list is set to val, and the list is auto-extended if necessary.
References _cl_string_list::allocated, cl_realloc(), _cl_string_list::data, _cl_string_list::lumpsize, and _cl_string_list::size.
Referenced by cl_string_list_append().
int cl_string_list_size | ( | cl_string_list | l | ) |
Gets the current size of a cl_string_list object (number of elements on the list).
References _cl_string_list::size.
Referenced by cl_make_set(), close_range(), cwbci_check_line(), main(), open_range(), parse_options(), and print_range_registry_line().
unsigned char* cl_string_maptable | ( | CorpusCharset | charset, | |
int | flags | |||
) |
Gets a specified character mapping table for use in regular expressions.
charset | The character set of this corpus. Currently ignored. | |
flags | The flags that specify which table is required. Can be IGNORE_CASE and/or IGNORE_DIAC. |
References IGNORE_CASE, IGNORE_DIAC, latin1_identity_tab, latin1_identity_tab_init, latin1_nocase_nodiac_tab, latin1_nocase_nodiac_tab_init, latin1_nocase_tab, and latin1_nodiac_tab.
Referenced by cl_string_canonical(), and SortSubcorpus().
int ClosePositionStream | ( | PositionStream * | ps | ) |
Deletes a PositionStream object.
References BSclose().
Referenced by compress_reversed_index(), and decompress_check_reversed_index().
int* collect_matches | ( | Attribute * | attribute, | |
int * | word_ids, | |||
int | number_of_words, | |||
int | sort, | |||
int * | size_of_table, | |||
int * | restrictor_list, | |||
int | restrictor_list_size | |||
) |
Gets a list of corpus positions matching a list of ids.
This function returns an (ordered) list of all corpus positions which matches one of the ids given in the list of ids. The table is allocated with malloc, so free it when you don't need any more.
The list itself is returned; its size is placed in size_of_table. This size is, of course, the same as the cumulative id frequency of the ids (because each corpus position matching one of the ids is added into the list).
BEWARE: when the id list is rather big or there are highly-frequent ids in the id list (for example, after a call to collect_matching_ids with the pattern ".*") this will give a copy of the corpus -- for which you probably don't have enough memory!!! It is therefore a good idea to call cumulative_id_frequency before and to introduce some kind of bias.
A note on the last two parameters, which are currently unused: restrictor_list is a list of integer pairs [a,b] which means that the returned value only contains positions which fall within at least one of these intervals. The list must be sorted by the start positions, and secondarily by b. restrictor_list_size is the number of integers in this list, NOT THE NUMBER OF PAIRS. WARNING: CURRENTLY UNIMPLEMENTED {NB -- this descrtiption of restrictor_list_size DOESN'T MATCH the one for get_positions(), which this function calls...
REMEMBER: this monster returns a list of corpus indices, not a list of ids.
attribute | The P-attribute we are looking in | |
word_ids | A list of item ids (i.e. id codes for items on this attribute). | |
number_of_words | The length of this list. | |
sort | boolean: return sorted list? | |
size_of_table | The size of the allocated table will be placed here. | |
restrictor_list | See function description. | |
restrictor_list_size | See function description. |
References ATT_POS, CDA_EIDORNG, CDA_ENODATA, CDA_OK, cderrno, check_arg, cl_malloc(), CompLexiconIdx, cumulative_id_frequency(), ensure_component(), get_positions(), intcompare(), and TComponent::size.
Referenced by calculate_initial_matchlist_1(), get_corpus_positions(), and get_matched_corpus_positions().
int* collect_matching_ids | ( | Attribute * | attribute, | |
char * | pattern, | |||
int | flags, | |||
int * | number_of_matches | |||
) |
Gets a list of the ids of those items on a given Attribute that match a particular regular-expression pattern.
The pattern is interpreted with the CL regex engine, q.v.
The function returns a pointer to a sequence of ints of size number_of_matches. The list is allocated with malloc(), so do a cl_free() when you don't need it any more.
attribute | The p-attribute to look on. | |
pattern | String containing the pattern against which to match each item on the attribute | |
flags | Flags for the regular expression system via cl_new_regex. | |
number_of_matches | This is set to the number of item ids found, i.e. the size of the returned buffer. |
References _CL_Regex::anchor_end, _CL_Regex::anchor_start, ATT_POS, _CL_Regex::buffer, CDA_EBADREGEX, CDA_ENODATA, CDA_OK, cderrno, check_arg, cl_calloc(), cl_debug, cl_delete_regex(), cl_free, cl_malloc(), cl_new_regex(), cl_regex_error, cl_regex_optimised(), cl_string_canonical(), CompLexicon, CompLexiconIdx, TMblob::data, TComponent::data, ensure_component(), _CL_Regex::flags, _CL_Regex::grain, _CL_Regex::grain_len, _CL_Regex::grains, IGNORE_CASE, IGNORE_DIAC, _CL_Regex::iso_string, _CL_Regex::jumptable, latin1, TComponent::size, and word.
Referenced by get_matched_corpus_positions(), and OptimizeStringConstraint().
int cumulative_id_frequency | ( | Attribute * | attribute, | |
int * | word_ids, | |||
int | number_of_words | |||
) |
Calculates the total frequency of all items on a list of item IDs.
This function returns the sum of the word frequencies of words, which is an array of word_ids with length number_of_words.
The result is therefore the number of corpus positions which match one of the words.
attribute | P-attribute on which these items are found. | |
word_ids | An array of item IDs. | |
number_of_words | Length of the word_ids array. |
References ATT_POS, CDA_ENODATA, CDA_OK, cderrno, check_arg, and get_id_frequency().
Referenced by collect_matches().
void describe_corpus | ( | Corpus * | corpus | ) |
Prints a description of the corpus to STDOUT.
References _Attribute::any, TCorpus::attributes, describe_attribute(), TCorpus::id, TCorpus::info_file, TCorpus::name, TCorpus::path, TCorpus::registry_dir, and TCorpus::registry_name.
Referenced by main().
int drop_corpus | ( | Corpus * | corpus | ) |
Deletes a Corpus object.
corpus | The Corpus to delete |
References TCorpus::admin, attr_drop_attribute(), TCorpus::attributes, cl_free, FreeIDList(), TCorpus::groupAccessList, TCorpus::hostAccessList, TCorpus::id, TCorpus::info_file, TCorpus::name, TCorpus::next, TCorpus::nr_of_loads, TCorpus::path, TCorpus::registry_dir, TCorpus::registry_name, and TCorpus::userAccessList.
Referenced by cleanup(), main(), setup_corpus(), and usage().
Finds an attribute that matches the specified parameters, if one exists.
corpus | The corpus in which to search for the attribute. | |
attribute_name | The name of the attribute (i.e. the handle it has in the registry file) | |
type | Type of attribute to be searched for. | |
data | NOT USED. |
References _Attribute::any, TCorpus::attributes, STREQ, and _Attribute::type.
Referenced by compute_grouping(), ComputePrintStructures(), do_attribute_show(), do_Description(), do_IDReference(), do_LabelReference(), do_SimpleVariableReference(), do_StringConstraint(), do_StructuralContext(), drop_attribute(), evaluate_target(), findcorpus(), FunctionCall(), get_matched_corpus_positions(), main(), prepare_AlignmentConstraints(), printAlignedStrings(), read_mapping(), RecomputeAL(), red_factor(), Setop(), setup_attribute(), SortSubcorpus(), SystemCorpusSize(), update_context_descriptor(), verify_context_descriptor(), and VerifyList().
Corpus* find_corpus | ( | char * | registry_dir, | |
char * | registry_name | |||
) |
Gets a pointer to the Corpus object with the specified CWB-name and registry location.
(Works by searching the loaded_corpora global linked list.)
registry_dir | The registry directory. | |
registry_name | The CWB name of the corpus. |
References cl_standard_registry, TCorpus::next, TCorpus::registry_dir, TCorpus::registry_name, and STREQ.
Referenced by setup_corpus().
int get_alg_attribute | ( | Attribute * | attribute, | |
int | position, | |||
int * | source_corpus_start, | |||
int * | source_corpus_end, | |||
int * | aligned_corpus_start, | |||
int * | aligned_corpus_end | |||
) |
Gets the corpus positions of an alignment on the given align-attribute.
This is for old-style alignments only: it doesn't (can't) deal with extended alignments. Depracated: use cl_alg2cpos instead (but note its parameters are not identical).
attribute | The align-attribute to look on. | |
position | The corpus position {??} of the alignment whose positions are wanted. | |
source_corpus_start | Location to put source corpus start position. | |
source_corpus_end | Location to put source corpus end position. | |
aligned_corpus_start | Location to put target corpus start position. | |
aligned_corpus_end | Location to put target corpus end position. |
References ATT_ALIGN, CDA_ENODATA, CDA_EPOSORNG, CDA_OK, cderrno, check_arg, CompAlignData, TMblob::data, TComponent::data, ensure_component(), get_alignment(), and TComponent::size.
int get_attribute_size | ( | Attribute * | attribute | ) |
Gets the maximum position on this P-attribute (ie the size of the attribute).
The result of this function is equal to the number of tokens in the attribute.
If the attribute's item sequence is compressed, this is read from the attribute's Huffman code descriptor block.
Otherwise, it is read from the size member of the Attribute's CompCorpus component.
References ATT_POS, CDA_ENODATA, CDA_OK, cderrno, check_arg, CompCorpus, CompHuffCodes, corpus, ensure_component(), POS_Attribute::hc, item_sequence_is_compressed(), _huffman_code_descriptor::length, _Attribute::pos, and TComponent::size.
Referenced by compose_kwic_line(), get_matched_corpus_positions(), get_positions(), OpenPositionStream(), Setop(), and SystemCorpusSize().
int get_bounds_of_nth_struc | ( | Attribute * | attribute, | |
int | struc_num, | |||
int * | struc_start, | |||
int * | struc_end | |||
) |
Retrieves the start-and-end corpus positions of a specified structure of the given s-attribute type.
attribute | An s-attribute. | |
struc_num | The instance of that s-attribute to retrieve (i.e. the struc_num'th instance of this s-attribute in the corpus). | |
struc_start | Location to put the starting corpus position. | |
struc_end | Location to put the ending corpus position. |
References ATT_STRUC, CDA_EIDXORNG, CDA_ENODATA, CDA_OK, cderrno, check_arg, CompStrucData, TMblob::data, TComponent::data, ensure_component(), and TComponent::size.
Referenced by calculate_ranges(), and feature_match().
int get_id_at_position | ( | Attribute * | attribute, | |
int | position | |||
) |
Gets the integer ID of the item at the specified position on the given p-attribute.
attribute | The P-attribute to look on. | |
position | The corpus position to look at. |
References _Attribute::any, ATT_POS, BSclose(), BSopen(), BSread(), BSseek(), CDA_ENODATA, CDA_EPOSORNG, CDA_OK, cderrno, check_arg, CompCorpus, CompHuffCodes, CompHuffSeq, CompHuffSync, COMPRESS_DEBUG, corpus, TMblob::data, TComponent::data, ensure_component(), POS_Attribute::hc, item_sequence_is_compressed(), _huffman_code_descriptor::length, _huffman_code_descriptor::min_code, _Attribute::pos, _huffman_code_descriptor::symbols, _huffman_code_descriptor::symindex, SYNCHRONIZATION, POS_Attribute::this_block, and POS_Attribute::this_block_nr.
Referenced by eval_bool(), feature_match(), get_leaf_value(), get_position_values(), and get_string_at_position().
int get_id_frequency | ( | Attribute * | attribute, | |
int | id | |||
) |
Gets the frequency of an item on this attribute.
attribute | The P-attribute to look on | |
id | Identifier of an item on this attribute. |
References ATT_POS, CDA_EIDXORNG, CDA_ENODATA, CDA_OK, cderrno, check_arg, CompCorpusFreqs, TMblob::data, TComponent::data, and ensure_component().
Referenced by call_predefined_function(), compute_code_lengths(), cumulative_id_frequency(), get_id_info(), get_positions(), and OpenPositionStream().
int get_id_from_sortidx | ( | Attribute * | attribute, | |
int | sort_index_position | |||
) |
Gets the ID code of the item at the specified position in the Attribute's sorted wordlist index.
attribute | The (positional) Attribute whose index is to be searched. | |
sort_index_position | The offset in the index where the ID code is to be found. |
References ATT_POS, CDA_EIDXORNG, CDA_ENODATA, CDA_OK, cderrno, check_arg, CompLexiconSrt, TMblob::data, TComponent::data, and ensure_component().
Referenced by do_show().
char* get_id_info | ( | Attribute * | attribute, | |
int | index, | |||
int * | freq, | |||
int * | slen | |||
) |
Gets the string of the item with the specified ID on the given p-attribute.
As well as returning the string, other information about the item is inserted into locations specified by other parameters.
attribute | The P-attribute to look on. | |
index | The ID of the item to look at. | |
freq | Will be set to the frequency of the item. | |
slen | Will be set to the string-length of the item. |
References ATT_POS, CDA_OK, cderrno, check_arg, get_id_frequency(), get_id_string_len(), and get_string_of_id().
Referenced by print_info().
int get_id_of_string | ( | Attribute * | attribute, | |
char * | id_string | |||
) |
Gets the ID code that corresponds to the specified string on the given P-attribute.
attribute | The (positional) Attribute to look the string up on | |
id_string | The string of an item on this attribute |
References ATT_POS, CDA_ENODATA, CDA_ENOSTRING, CDA_EOTHER, CDA_OK, cderrno, check_arg, cl_strcmp(), CompLexicon, CompLexiconIdx, CompLexiconSrt, TMblob::data, TComponent::data, ensure_component(), and TComponent::size.
Referenced by call_predefined_function(), get_corpus_positions(), map_token_to_class_number(), member_of_class_s(), OptimizeStringConstraint(), read_mapping(), show_features(), and VerifyVariable().
int get_id_range | ( | Attribute * | attribute | ) |
Gets the maximum id on this P-attribute (ie the range of the attribute's ID codes).
The result of this function is equal to the number of types in this attribute.
References ATT_POS, CDA_ENODATA, CDA_OK, cderrno, check_arg, CompLexiconIdx, ensure_component(), and TComponent::size.
Referenced by get_matched_corpus_positions(), get_positions(), OpenPositionStream(), and OptimizeStringConstraint().
int get_id_string_len | ( | Attribute * | attribute, | |
int | id | |||
) |
Calculates the length of the string that corresponds to the specified item on the given P-attribute.
attribute | The (positional) Attribute to look up the item on | |
id | Identifier of an item on this attribute. |
References ATT_POS, CDA_EIDORNG, CDA_ENODATA, CDA_EOTHER, CDA_OK, cderrno, check_arg, CompLexiconIdx, TMblob::data, TComponent::data, ensure_component(), get_string_of_id(), and TComponent::size.
Referenced by get_id_info().
int get_nr_of_strucs | ( | Attribute * | attribute, | |
int * | nr_strucs | |||
) |
Gets the number of instances of an s-attribute in the corpus.
Depracated: use cl_max_struc instead.
attribute | The s-attribute to count. | |
nr_strucs | The number of instances is put here. |
References ATT_STRUC, CDA_ENODATA, CDA_OK, cderrno, check_arg, CompStrucData, ensure_component(), and TComponent::size.
Referenced by calculate_ranges(), and cl_max_struc().
int get_num_of_struc | ( | Attribute * | attribute, | |
int | position, | |||
int * | struc_num | |||
) |
Gets the ID number of a structure (instance of an s-attribute) that is found at the given corpus position.
Depracated function: use cl_cpos2struc.
attribute | The s-attribute on which to search. | |
position | The corpus position to look for. | |
struc_num | Location where the number of the structure that is found will be put. |
References ATT_STRUC, CDA_ENODATA, CDA_ESTRUC, CDA_OK, cderrno, check_arg, CompStrucData, TMblob::data, TComponent::data, ensure_component(), get_previous_mark(), and TComponent::size.
Referenced by calculate_ranges(), cl_cpos2struc(), and structure_value_at_position().
int* get_positions | ( | Attribute * | attribute, | |
int | id, | |||
int * | freq, | |||
int * | restrictor_list, | |||
int | restrictor_list_size | |||
) |
Gets all the corpus positions where the specified item is found on the given P-attribute.
The restrictor list is a set of ranges in which instances of the item MUST occur to be collected by this function. If no restrictor list is specified (i.e. restrictor_list is NULL), then ALL corpus positions where the item occurs are returned.
This restrictor list has the form of a list of ranges {start,end} of size restrictor_list_size, that is, the number of ints in this area is 2 * restrictor_list_size!!!
attribute | The P-attribute to look on. | |
id | The id of the item to look for. | |
freq | The frequency of the specified item is written here. This will be 0 in the case of errors. | |
restrictor_list | A list of pairs of integers specifying ranges {start,end} in the corpus | |
restrictor_list_size | The number of PAIRS of ints in the restrictor list. |
References ATT_POS, BSclose(), BSopen(), BSseek(), CDA_EIDORNG, CDA_ENODATA, CDA_OK, cderrno, check_arg, cl_free, cl_malloc(), cl_realloc(), CompCompRF, CompCompRFX, CompRevCorpus, CompRevCorpusIdx, compute_ba(), TMblob::data, TComponent::data, ensure_component(), get_attribute_size(), get_id_frequency(), get_id_range(), inverted_file_is_compressed(), range, and read_golomb_code_bs().
Referenced by calculate_initial_matchlist_1(), and collect_matches().
int get_sortidxpos_of_id | ( | Attribute * | attribute, | |
int | id | |||
) |
Gets the position in the Attribute's sorted wordlist index of the item with the specified ID code.
This function is NOT YET IMPLEMENTED.
attribute | The (positional) Attribute whose index is to be searched | |
id | Identifier of an item on this attribute. |
References ATT_POS, CDA_ENODATA, CDA_ENYI, CDA_OK, cderrno, check_arg, CompLexiconSrt, and ensure_component().
char* get_string_at_position | ( | Attribute * | attribute, | |
int | position | |||
) |
Gets the string of the item at the specified position on the given p-attribute.
attribute | The P-attribute to look on. | |
position | The corpus position to look at. |
References ATT_POS, CDA_OK, cderrno, check_arg, get_id_at_position(), and get_string_of_id().
Referenced by get_leaf_value(), get_position_values(), and print_next_region().
char* get_string_of_id | ( | Attribute * | attribute, | |
int | id | |||
) |
Gets the string that corresponds to the specified item on the given P-attribute.
attribute | The Attribute to look the item up on | |
id | Identifier of an item on this attribute. |
References ATT_POS, CDA_EIDORNG, CDA_ENODATA, CDA_OK, cderrno, check_arg, CompLexicon, CompLexiconIdx, TMblob::data, TComponent::data, ensure_component(), and TComponent::size.
Referenced by call_predefined_function(), compute_code_lengths(), eval_bool(), get_id_info(), get_id_string_len(), get_string_at_position(), and print_mapping().
int get_struc_attribute | ( | Attribute * | attribute, | |
int | position, | |||
int * | struc_start, | |||
int * | struc_end | |||
) |
Gets the start and end positions of the instance of the given S-attribute found at the specified corpus position.
This function finds one particular instance of the S-attribute, and assigns its start and end points to the locations given as arguments.
attribute | The s-attribute to search. | |
position | The corpus position to search for. | |
struc_start | Location for the start position of the instance. | |
struc_end | Location for the end position of the instance. |
References ATT_STRUC, CDA_ENODATA, CDA_ESTRUC, CDA_OK, cderrno, check_arg, CompStrucData, TMblob::data, TComponent::data, ensure_component(), get_previous_mark(), and TComponent::size.
Referenced by calculate_ranges(), eval_bool(), get_leaf_value(), meet_mu(), show_position_values(), and simulate().
int inverted_file_is_compressed | ( | Attribute * | attribute | ) |
Check whether the index (inverted file) of the given P-attribute is compressed.
See comments in body of function for what counts as "compressed".
References ATT_POS, cderrno, check_arg, CompCompRF, CompCompRFX, component_state(), ComponentLoaded, ComponentUnloaded, CompRevCorpus, and CompRevCorpusIdx.
Referenced by get_positions(), and OpenPositionStream().
int item_sequence_is_compressed | ( | Attribute * | attribute | ) |
Checks whether the item sequence of the given P-attribute is compressed.
See comments in body of function for what counts as "compressed".
References ATT_POS, cderrno, check_arg, CompCorpus, CompHuffCodes, CompHuffSeq, CompHuffSync, component_state(), ComponentLoaded, ComponentUnloaded, POS_Attribute::hc, and _Attribute::pos.
Referenced by get_attribute_size(), get_id_at_position(), and load_component().
int nr_of_arguments | ( | Attribute * | attribute | ) |
Count the number of arguments on an attribute's dynamic argument list.
attribute | pointer to the Attribute object to analyse; it must be a dynamic attribute. |
References Dynamic_Attribute::arglist, ATT_DYN, ATTAT_VAR, CDA_OK, cderrno, check_arg, _Attribute::dyn, _DynArg::next, and _DynArg::type.
PositionStream OpenPositionStream | ( | Attribute * | attribute, | |
int | id | |||
) |
Creates a new PositionStream object.
attribute | The P-attribute to open the position stream on | |
id | The id that the new PositionStream will have. This the id of an item on the specified attribute. |
References ATT_POS, _position_stream_rec_::attribute, _position_stream_rec_::b, _position_stream_rec_::base, _position_stream_rec_::bs, BSopen(), BSseek(), CDA_EIDORNG, CDA_ENODATA, CDA_OK, cderrno, check_arg, CompCompRF, CompCompRFX, CompRevCorpus, CompRevCorpusIdx, compute_ba(), TMblob::data, TComponent::data, ensure_component(), get_attribute_size(), get_id_frequency(), get_id_range(), _position_stream_rec_::id, _position_stream_rec_::id_freq, inverted_file_is_compressed(), _position_stream_rec_::is_compressed, _position_stream_rec_::last_pos, _position_stream_rec_::nr_items, and range.
Referenced by compress_reversed_index(), and decompress_check_reversed_index().
int ReadPositionStream | ( | PositionStream | ps, | |
int * | buffer, | |||
int | buffer_size | |||
) |
Reads corpus positions from a position stream to a buffer.
ps | The position stream to read. | |
buffer | Location to put the resulting item positions. | |
buffer_size | Maximum number of item positions to read. (Fewer will be read if fewer are available). |
References _position_stream_rec_::b, _position_stream_rec_::base, _position_stream_rec_::bs, _position_stream_rec_::id_freq, _position_stream_rec_::is_compressed, _position_stream_rec_::last_pos, _position_stream_rec_::nr_items, and read_golomb_code_bs().
Referenced by compress_reversed_index(), and decompress_check_reversed_index().
Corpus* setup_corpus | ( | char * | registry_dir, | |
char * | registry_name | |||
) |
Creates a Corpus object.
registry_dir | Path to the CWB registry directory from which the corpus is to be loaded. This may be NULL, in which case the default registry directory is used. | |
registry_name | The CWB-name of the indexed corpus to load (in the all-lowercase form) |
References central_corpus_directory(), check_access_conditions(), cl_free, cl_strdup(), cl_string_canonical(), corpus, cregin, cregin_name, cregin_path, cregparse(), cregrestart(), drop_corpus(), find_corpus(), find_corpus_registry(), TCorpus::id, IGNORE_CASE, TCorpus::next, TCorpus::nr_of_loads, TCorpus::registry_dir, and TCorpus::registry_name.
Referenced by GetSystemCorpus(), main(), and printAlignedStrings().
int structure_has_values | ( | Attribute * | attribute | ) |
Checks whether this s-attribute has attribute values.
References ATT_STRUC, CDA_OK, cderrno, check_arg, component_state(), ComponentLoaded, ComponentUnloaded, CompStrucAVS, CompStrucAVX, Struc_Attribute::has_attribute_values, and _Attribute::struc.
Referenced by ComputePrintStructures(), do_LabelReference(), structure_value(), and update_context_descriptor().
char* structure_value | ( | Attribute * | attribute, | |
int | struc_num | |||
) |
Gets the value that is associated with the specified instance of the given s-attribute.
attribute | An S-attribute. | |
struc_num | ID of the structure whose value is wanted (ie, function gets value of struc_num'th instance of this s-attribute) |
References ATT_STRUC, CDA_EIDXORNG, CDA_EINTERNAL, CDA_ENODATA, CDA_OK, cderrno, check_arg, CompStrucAVS, CompStrucAVX, TMblob::data, TComponent::data, ensure_component(), s_v_comp(), TComponent::size, and structure_has_values().
Referenced by structure_value_at_position().
char* structure_value_at_position | ( | Attribute * | struc, | |
int | position | |||
) |
Gets the value associated with the instance of the given s-attribute that occurs at the specified corpus position.
struc | The s-attribute to search through. | |
position | The corpus position being queried. |
References get_num_of_struc(), and structure_value().
Referenced by get_leaf_value(), and get_print_attribute_values().
int cderrno |
Error number for CL: is set after access to any of various corpus-data-access functions.
Referenced by call_dynamic_attribute(), call_predefined_function(), cdperror(), check_alignment_constraints(), cl_alg2cpos(), cl_cpos2alg(), cl_cpos2boundary(), cl_cpos2struc(), cl_has_extended_alignment(), cl_make_set(), cl_max_alg(), cl_max_struc(), cl_new_regex(), cl_set_intersection(), cl_set_size(), collect_matches(), collect_matching_ids(), compress_reversed_index(), compute_code_lengths(), cumulative_id_frequency(), decode_check_huff(), decompress_check_reversed_index(), do_cqi_cl_regex2id(), do_show(), ensure_corpus_size(), eval_bool(), get_alg_attribute(), get_attribute_size(), get_bounds_of_nth_struc(), get_corpus_positions(), get_id_at_position(), get_id_frequency(), get_id_from_sortidx(), get_id_info(), get_id_of_string(), get_id_range(), get_id_string_len(), get_leaf_value(), get_nr_of_strucs(), get_num_of_struc(), get_position_values(), get_positions(), get_sortidxpos_of_id(), get_string_at_position(), get_string_of_id(), get_struc_attribute(), inverted_file_is_compressed(), item_sequence_is_compressed(), map_token_to_class_number(), meet_mu(), member_of_class_s(), nr_of_arguments(), OpenPositionStream(), OptimizeStringConstraint(), print_info(), read_mapping(), send_cl_error(), Setop(), show_position_values(), structure_has_values(), and structure_value().
char cl_regex_error[] |
The error message from (POSIX) regex compilation are placed in this buffer if cl_new_regex() fails.
Referenced by cl_new_regex(), and collect_matching_ids().