4ba0a7d92cc93673915bb6f24ae81435ea179ce3
hiram
  Wed Jan 31 17:02:58 2024 -0800
beginning to add a searchable table of genome meta data refs #23589;

diff --git src/hg/inc/genomeData.h src/hg/inc/genomeData.h
new file mode 100644
index 0000000..a6fbcaa
--- /dev/null
+++ src/hg/inc/genomeData.h
@@ -0,0 +1,117 @@
+/* genomeData.h was originally generated by the autoSql program, which also 
+ * generated genomeData.c and genomeData.sql.  This header links the database and
+ * the RAM representation of objects. */
+
+#ifndef GENOMEDATA_H
+#define GENOMEDATA_H
+
+#include "jksql.h"
+#define GENOMEDATA_NUM_COLS 37
+
+extern char *genomeDataCommaSepFieldNames;
+
+struct genomeData
+/* SQL table for NCBI assembly_summary data. */
+    {
+    struct genomeData *next;  /* Next in singly linked list. */
+    char *assemblyAccession;	/* assemblyAccession */
+    char *bioproject;	/* bioproject */
+    char *biosample;	/* biosample */
+    char *wgsMaster;	/* wgsMaster */
+    char *refseqCategory;	/* refseqCategory */
+    unsigned *taxId;	/* taxId */
+    unsigned *speciesTaxid;	/* speciesTaxid */
+    char *organismName;	/* organismName */
+    char *infraspecificName;	/* infraspecificName */
+    char *isolate;	/* isolate */
+    char *versionStatus;	/* versionStatus */
+    char *assemblyLevel;	/* assemblyLevel */
+    char *releaseType;	/* releaseType */
+    char *genomeRep;	/* genomeRep */
+    char *seqRelDate;	/* seqRelDate */
+    char *asmName;	/* asmName */
+    char *asmSubmitter;	/* asmSubmitter */
+    char *gbrsPairedAsm;	/* gbrsPairedAsm */
+    char *pairedAsmComp;	/* pairedAsmComp */
+    char *ftpPath;	/* ftpPath */
+    char *excludedFromRefseq;	/* excludedFromRefseq */
+    char *relationToTypeMaterial;	/* relationToTypeMaterial */
+    unsigned char *assemblyType;	/* assemblyType */
+    char *phyloGroup;	/* phyloGroup */
+    long long *genomeSize;	/* genomeSize */
+    long long *genomeSizeUngapped;	/* genomeSizeUngapped */
+    float *gcPercent;	/* gcPercent */
+    unsigned short *repliconCount;	/* repliconCount */
+    unsigned *scaffoldCount;	/* scaffoldCount */
+    unsigned *contigCount;	/* contigCount */
+    char *annotationProvider;	/* annotationProvider */
+    char *annotationName;	/* annotationName */
+    char *annotationDate;	/* annotationDate */
+    char *totalGeneCount;	/* totalGeneCount */
+    unsigned *proteinCodingGeneCount;	/* proteinCodingGeneCount */
+    char *nonCodingGeneCount;	/* nonCodingGeneCount */
+    char *pubmedId;	/* pubmedId */
+    };
+
+void genomeDataStaticLoadWithNull(char **row, struct genomeData *ret);
+/* Load a row from genomeData table into ret.  The contents of ret will
+ * be replaced at the next call to this function. */
+
+struct genomeData *genomeDataLoadByQuery(struct sqlConnection *conn, char *query);
+/* Load all genomeData from table that satisfy the query given.  
+ * Where query is of the form 'select * from example where something=something'
+ * or 'select example.* from example, anotherTable where example.something = 
+ * anotherTable.something'.
+ * Dispose of this with genomeDataFreeList(). */
+
+void genomeDataSaveToDb(struct sqlConnection *conn, struct genomeData *el, char *tableName, int updateSize);
+/* Save genomeData as a row to the table specified by tableName. 
+ * As blob fields may be arbitrary size updateSize specifies the approx size
+ * of a string that would contain the entire query. Arrays of native types are
+ * converted to comma separated strings and loaded as such, User defined types are
+ * inserted as NULL. This function automatically escapes quoted strings for mysql. */
+
+struct genomeData *genomeDataLoadWithNull(char **row);
+/* Load a genomeData from row fetched with select * from genomeData
+ * from database.  Dispose of this with genomeDataFree(). */
+
+struct genomeData *genomeDataLoadAll(char *fileName);
+/* Load all genomeData from whitespace-separated file.
+ * Dispose of this with genomeDataFreeList(). */
+
+struct genomeData *genomeDataLoadAllByChar(char *fileName, char chopper);
+/* Load all genomeData from chopper separated file.
+ * Dispose of this with genomeDataFreeList(). */
+
+#define genomeDataLoadAllByTab(a) genomeDataLoadAllByChar(a, '\t');
+/* Load all genomeData from tab separated file.
+ * Dispose of this with genomeDataFreeList(). */
+
+struct genomeData *genomeDataCommaIn(char **pS, struct genomeData *ret);
+/* Create a genomeData out of a comma separated string. 
+ * This will fill in ret if non-null, otherwise will
+ * return a new genomeData */
+
+void genomeDataFree(struct genomeData **pEl);
+/* Free a single dynamically allocated genomeData such as created
+ * with genomeDataLoad(). */
+
+void genomeDataFreeList(struct genomeData **pList);
+/* Free a list of dynamically allocated genomeData's */
+
+void genomeDataOutput(struct genomeData *el, FILE *f, char sep, char lastSep);
+/* Print out genomeData.  Separate fields with sep. Follow last field with lastSep. */
+
+#define genomeDataTabOut(el,f) genomeDataOutput(el,f,'\t','\n');
+/* Print out genomeData as a line in a tab-separated file. */
+
+#define genomeDataCommaOut(el,f) genomeDataOutput(el,f,',',',');
+/* Print out genomeData as a comma separated list including final comma. */
+
+void genomeDataJsonOutput(struct genomeData *el, FILE *f);
+/* Print out genomeData in JSON format. */
+
+/* -------------------------------- End autoSql Generated Code -------------------------------- */
+
+#endif /* GENOMEDATA_H */
+