From 0b27f33d2eefcd05f46d60c9aaa15a5eee25e5b3 Mon Sep 17 00:00:00 2001
From: Nick Sweeting <git@nicksweeting.com>
Date: Wed, 24 Apr 2019 04:06:54 -0400
Subject: [PATCH] fix sql link parsing and writing

---
 archivebox/legacy/index.py       | 6 ++++--
 archivebox/legacy/logs.py        | 2 +-
 archivebox/legacy/storage/sql.py | 2 +-
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/archivebox/legacy/index.py b/archivebox/legacy/index.py
index 2ce7bb82..29b355db 100644
--- a/archivebox/legacy/index.py
+++ b/archivebox/legacy/index.py
@@ -245,10 +245,12 @@ def load_main_index(out_dir: str=OUTPUT_DIR, warn: bool=True) -> List[Link]:
 
     all_links: List[Link] = []
     all_links = list(parse_json_main_index(out_dir))
-    links_from_sql = list(parse_sql_main_index())
+    links_from_sql = list(parse_sql_main_index(out_dir))
 
-    if warn and not set(l.url for l in all_links) == set(l['url'] for l in links_from_sql):
+    if warn and not set(l.url for l in all_links) == set(l.url for l in links_from_sql):
         stderr('{red}[!] Warning: SQL index does not match JSON index!{reset}'.format(**ANSI))
+        stderr('    To repair the index and re-import any orphaned links run:')
+        stderr('        archivebox init')
 
     return all_links
 
diff --git a/archivebox/legacy/logs.py b/archivebox/legacy/logs.py
index 8cb13629..e0b34301 100644
--- a/archivebox/legacy/logs.py
+++ b/archivebox/legacy/logs.py
@@ -60,7 +60,7 @@ def log_indexing_process_started(num_links: int):
     start_ts = datetime.now()
     _LAST_RUN_STATS.index_start_ts = start_ts
     print()
-    print('{green}[*] [{}] Updating {} links in main index...{reset}'.format(
+    print('{green}[*] [{}] Writing {} links to main index...{reset}'.format(
         start_ts.strftime('%Y-%m-%d %H:%M:%S'),
         num_links,
         **ANSI,
diff --git a/archivebox/legacy/storage/sql.py b/archivebox/legacy/storage/sql.py
index be6bfbe2..302208ae 100644
--- a/archivebox/legacy/storage/sql.py
+++ b/archivebox/legacy/storage/sql.py
@@ -15,7 +15,7 @@ def parse_sql_main_index(out_dir: str=OUTPUT_DIR) -> Iterator[Link]:
     from core.models import Page
 
     return (
-        page.as_json(*Page.keys)
+        Link.from_json(page.as_json(*Page.keys))
         for page in Page.objects.all()
     )