-rw-r--r-- | src/load/load_asn.c | 173 | ||||
-rw-r--r-- | src/load/load_asn.h | 24 | ||||
-rw-r--r-- | src/load/load_features.c | 167 | ||||
-rw-r--r-- | src/load/load_features.h | 12 |
4 files changed, 376 insertions, 0 deletions
diff --git a/src/load/load_asn.h b/src/load/load_asn.h new file mode 100644 index 0000000..a7d54db --- a/dev/null +++ b/src/load/load_asn.h | |||
@@ -0,0 +1,24 @@ | |||
1 | #ifndef LOAD_ASN_H | ||
2 | #define LOAD_ASN_H | ||
3 | |||
4 | #include <hdf5.h> | ||
5 | |||
6 | /* | ||
7 | * Load the features and other meta-data pulled from Entrez via eFetch | ||
8 | * as ASN.1. | ||
9 | * | ||
10 | * Test: gi|453644 | ||
11 | * | ||
12 | * Retrieving the ASN.1 file via eFetch for gi|453644 worked smoothly | ||
13 | * however the hierarchy of the ASN.1 is difficult to align with other | ||
14 | * data by GI. This is due to the Bioseqset returned lacking | ||
15 | * identifiers and the gi|453644 appearing as a Bioseq member of the | ||
16 | * set. It is positioned on the same hierarchical level as gi|453643. | ||
17 | * The containing set includes the PUB records. Comparatively the XML | ||
18 | * files returned via the same process list the gi|453644 at the top | ||
19 | * of the hierarchy and above the PUB records. This output appears to | ||
20 | * be more consistent with the perspective requested in the input. | ||
21 | */ | ||
22 | void load_asn (hid_t file_id, const char* file_name); | ||
23 | |||
24 | #endif // LOAD_ASN_H | ||