Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Option to disable street name expansion for near dupes #594

Open
wants to merge 6 commits into
base: master
Choose a base branch
from
Open

Option to disable street name expansion for near dupes #594

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
0de3d81
Add flag to skip root expansion for near dupe street components
tresata-gbernard Jun 7, 2021
df32faf
Merge branch 'master' into feat-near-dupe-root
tresata-gbernard Jun 7, 2021
9030d84
make root options setting more explicit for street components
tresata-gbernard Jun 7, 2021
db9a269
Merge branch 'master' into feat-near-dupe-root
koertkuipers Jul 25, 2022
c601005
cleanup formatting
koertkuipers Jul 25, 2022
eb479a9
clarify that we are only enabling/disabling root expansion for street…
koertkuipers Jul 25, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions src/libpostal.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,8 @@ static libpostal_normalize_options_t LIBPOSTAL_DEFAULT_OPTIONS = {
.drop_english_possessives = true,
.delete_apostrophes = true,
.expand_numex = true,
.roman_numerals = true
.roman_numerals = true,
.root = true
};

libpostal_normalize_options_t libpostal_get_default_options(void) {
Expand Down Expand Up @@ -78,7 +79,8 @@ static libpostal_near_dupe_hash_options_t LIBPOSTAL_NEAR_DUPE_HASH_DEFAULT_OPTIO
.geohash_precision = DEFAULT_NEAR_DUPE_GEOHASH_PRECISION,
.name_and_address_keys = true,
.name_only_keys = false,
.address_only_keys = false
.address_only_keys = false,
.street_root = true
};

libpostal_near_dupe_hash_options_t libpostal_get_near_dupe_hash_default_options(void) {
Expand Down
4 changes: 4 additions & 0 deletions src/libpostal.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,6 +133,9 @@ typedef struct libpostal_normalize_options {
bool expand_numex;
bool roman_numerals;

// Expansion options
bool root;

} libpostal_normalize_options_t;

LIBPOSTAL_EXPORT libpostal_normalize_options_t libpostal_get_default_options(void);
Expand Down Expand Up @@ -202,6 +205,7 @@ typedef struct libpostal_near_dupe_hash_options {
bool name_and_address_keys;
bool name_only_keys;
bool address_only_keys;
bool street_root;
} libpostal_near_dupe_hash_options_t;

LIBPOSTAL_EXPORT libpostal_near_dupe_hash_options_t libpostal_get_near_dupe_hash_default_options(void);
Expand Down
5 changes: 3 additions & 2 deletions src/near_dupe.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,8 +150,8 @@ cstring_array *expanded_component_combined(char *input, libpostal_normalize_opti

size_t num_root_expansions = 0;
cstring_array *root_expansions = expand_address_root(input, options, &num_root_expansions);
if (num_root_expansions == 0) {

if (!options.root || num_root_expansions == 0) {
cstring_array_destroy(root_expansions);
*n = num_expansions;
return expansions;
Expand Down Expand Up @@ -706,6 +706,7 @@ cstring_array *near_dupe_hashes_languages(size_t num_components, char **labels,
remove_spaces = true;
log_debug("Doing street expansions for %s\n", place->street);
normalize_options.address_components = LIBPOSTAL_ADDRESS_STREET | LIBPOSTAL_ADDRESS_ANY;
normalize_options.root = options.street_root;
street_expansions = expanded_component_combined(place->street, normalize_options, remove_spaces, &num_street_expansions);
log_debug("Got %zu street expansions\n", num_street_expansions);
}
Expand Down