Merge branch 'master' of github.com:adamhrv/vframe_check_api

4 files changed, 21 insertions, 17 deletions

diff --git a/TODO.md b/TODO.md
new file mode 100644
index 0000000..97347af
--- /dev/null
+++ b/TODO.md
@@ -0,0 +1,12 @@
+# VFRAME Check API
+
+ToDo
+
+- deploy demo app to digital ocean
+- add post request with image URL
+- look into Docker Compose
+- wait for new 3GB sample set, produce new report
+- add upload-demo page to see resuluts, change threshold
+- add system status page
+- add authentication (htpasswd should be ok, unless you want to do API key)\
+- clean up HTML report and add PDF report
\ No newline at end of file
diff --git a/check/commands/phash/report.py b/check/commands/phash/report.py
index 362480d..a2de9aa 100644
--- a/check/commands/phash/report.py
+++ b/check/commands/phash/report.py
@@ -67,35 +67,24 @@ def cli(ctx, opt_fp_in, opt_fp_out, opt_recursive, opt_thresh, opt_slice):
   # Deduplicate the list of images
   log.info('Deduplicating images...')
   duplicates = []
+  names_added = []
   for sha256_a, im_obj_a in tqdm(ims_meta.copy().items()):  
     for sha256_b, im_obj_b in ims_meta.copy().items():
-      if sha256_a == sha256_b:
+      if sha256_a == sha256_b or im_obj_b['fname'] in names_added:
         continue
       d = abs(im_obj_a['imhash'] - im_obj_b['imhash'])
       if d <= opt_thresh:
         # mark B as a duplicate of A
-        ims_meta[sha256_b]['duplicate'] = sha256_a
+        #ims_meta[sha256_b]['duplicate'] = sha256_a
         duplicates.append({'sha256_a': sha256_a, 'fname_a': im_obj_a['fname'], 
           'sha256_b': sha256_b, 'fname_b': im_obj_b['fname'], 'score': d})
         ims_meta.pop(sha256_b)
+        names_added.append(im_obj_a['fname'])
 
   n_dupes = sum(1 for k,v in ims_meta.items() if v['duplicate'] is not None) 
   log.info(f'Found {n_dupes}')
 
-
-  #im_list = [v for k,v in ims_meta.items()] # dict to list of dicts
   df_items = pd.DataFrame.from_dict(duplicates)
-  #df_items.drop(['imhash', 'filepath'], axis=1, inplace=True)
   file_utils.ensure_dir(opt_fp_out)
   log.info(f'Writing: {opt_fp_out}')
-  df_items.to_csv(opt_fp_out, index=False)
-
-  # generate HTML
-  # copy images to another directory
-  # import shutil
-  # file_utils.ensure_dir(opt_fp_dir_copyto)
-  # for sha256, im_meta in ims_meta.items():
-  #   src = im_meta['filepath']
-  #   dst = join(opt_fp_dir_copyto, f'{sha256}.jpg')
-  #   # dst = join(opt_fp_dir_copyto, f"{im_meta['fname']}")
-  #   shutil.copy(src, dst)
\ No newline at end of file
+  df_items.to_csv(opt_fp_out, index=False)
\ No newline at end of file
diff --git a/check/static/assets/css.css b/check/static/assets/css.css
index 3f05bd9..d2ef116 100755
--- a/check/static/assets/css.css
+++ b/check/static/assets/css.css
@@ -326,6 +326,9 @@ kbd {
 .img_match{
   max-width:300px 
 }
+table.image_group{
+  margin-bottom:100px;
+}
 td.result_txt{
   vertical-align: top;
 }
diff --git a/check/static/perceptual_hash_report.html b/check/static/perceptual_hash_report.html
index 566a058..83748fa 100644
--- a/check/static/perceptual_hash_report.html
+++ b/check/static/perceptual_hash_report.html
@@ -8,7 +8,7 @@
   
   {% for fname_a, image_group in image_groups %}
   <h3>Duplicates for {{ fname_a }}</h3>
-  <table>
+  <table class="image_group">
     <tr>
       <th>Image A</th>
       <th>Image B</th>