GEDCOM: duplicate-aware import + typed name/attribute mapping

Duplicate detection (the "merge / skip / overwrite" the user asked for):
- New POST /gedcom/preview dry-runs the file and flags incoming people that
  resemble existing ones (name similarity via difflib + birth-year guard;
  high/medium score). No writes.
- /gedcom/import takes default_action (new|skip|merge|overwrite) + per-xref
  resolutions {xref: {action, target_id}}:
    new       create as a new person (current behavior)
    skip      link families to the existing person, copy nothing
    merge     attach the incoming names (as alternates), events, citations,
              and notes onto the existing person
    overwrite soft-delete the existing person, import the incoming one fresh
  Relationship creation is deduped so a merge can't double an edge.

Richer record mapping (covers the user's repo's GEDCOM):
- Multiple NAME records honor their TYPE; _MARNM (and NICK) import as typed
  alternate names — maiden stays primary, married becomes a "married" Name.
- RELI -> a "religion" event with the value in detail; OCCU/EDUC values too.
- NOTE -> person notes (and event notes); NOTE/RELI are no longer "unmapped".
- Export round-trips name TYPE.

Verified against the user's 2185-person export: 0 unmapped tags. 48 tests pass.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-07 10:35:55 -04:00
parent 04ccdbf96a
commit 5824e70895
7 changed files with 1047 additions and 90 deletions
+108 -1
View File
@@ -557,6 +557,27 @@ export interface paths {
patch: operations["update_media_api_v1_trees__tree_id__media__media_id__patch"];
trace?: never;
};
"/api/v1/trees/{tree_id}/gedcom/preview": {
parameters: {
query?: never;
header?: never;
path?: never;
cookie?: never;
};
get?: never;
put?: never;
/**
* Preview Gedcom
* @description Dry run: report counts and incoming people that look like duplicates of
* existing ones, so the user can choose how to resolve each before importing.
*/
post: operations["preview_gedcom_api_v1_trees__tree_id__gedcom_preview_post"];
delete?: never;
options?: never;
head?: never;
patch?: never;
trace?: never;
};
"/api/v1/trees/{tree_id}/gedcom/import": {
parameters: {
query?: never;
@@ -566,7 +587,12 @@ export interface paths {
};
get?: never;
put?: never;
/** Import Gedcom */
/**
* Import Gedcom
* @description Import a GEDCOM. ``default_action`` (new|skip|merge|overwrite) applies to
* incoming people that match an existing one; ``resolutions`` is a JSON object
* {xref: {action, target_id}} overriding it per record.
*/
post: operations["import_gedcom_api_v1_trees__tree_id__gedcom_import_post"];
delete?: never;
options?: never;
@@ -599,6 +625,21 @@ export interface components {
Body_import_gedcom_api_v1_trees__tree_id__gedcom_import_post: {
/** File */
file: string;
/**
* Default Action
* @default new
*/
default_action?: string;
/**
* Resolutions
* @default {}
*/
resolutions?: string;
};
/** Body_preview_gedcom_api_v1_trees__tree_id__gedcom_preview_post */
Body_preview_gedcom_api_v1_trees__tree_id__gedcom_preview_post: {
/** File */
file: string;
};
/** Body_upload_media_api_v1_trees__tree_id__media_post */
Body_upload_media_api_v1_trees__tree_id__media_post: {
@@ -683,6 +724,26 @@ export interface components {
detail?: string | null;
confidence?: components["schemas"]["CitationConfidence"] | null;
};
/** DuplicateMatch */
DuplicateMatch: {
/** Xref */
xref: string;
/** Incoming Name */
incoming_name: string;
/** Incoming Birth Year */
incoming_birth_year?: string | null;
/**
* Existing Person Id
* Format: uuid
*/
existing_person_id: string;
/** Existing Name */
existing_name: string;
/** Existing Birth Year */
existing_birth_year?: string | null;
/** Score */
score: string;
};
/** EventCreate */
EventCreate: {
/** Event Type */
@@ -777,6 +838,17 @@ export interface components {
/** Detail */
detail?: components["schemas"]["ValidationError"][];
};
/** ImportPreview */
ImportPreview: {
/** Counts */
counts: {
[key: string]: number;
};
/** Potential Duplicates */
potential_duplicates: components["schemas"]["DuplicateMatch"][];
/** Unmapped Tags */
unmapped_tags: string[];
};
/** ImportReport */
ImportReport: {
/** Counts */
@@ -2845,6 +2917,41 @@ export interface operations {
};
};
};
preview_gedcom_api_v1_trees__tree_id__gedcom_preview_post: {
parameters: {
query?: never;
header?: never;
path: {
tree_id: string;
};
cookie?: never;
};
requestBody: {
content: {
"multipart/form-data": components["schemas"]["Body_preview_gedcom_api_v1_trees__tree_id__gedcom_preview_post"];
};
};
responses: {
/** @description Successful Response */
200: {
headers: {
[name: string]: unknown;
};
content: {
"application/json": components["schemas"]["ImportPreview"];
};
};
/** @description Validation Error */
422: {
headers: {
[name: string]: unknown;
};
content: {
"application/json": components["schemas"]["HTTPValidationError"];
};
};
};
};
import_gedcom_api_v1_trees__tree_id__gedcom_import_post: {
parameters: {
query?: never;