1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
|
import argparse
import sqlite3
import sys
from pathlib import Path
try:
import openpyxl
except ImportError:
print("Error: openpyxl is required. Install it with 'pip install openpyxl'.")
sys.exit(1)
BASE_DIR = Path(__file__).resolve().parent
DB_DIR = BASE_DIR / "incoming_uploads" / "sqlite_output"
SOURCES = [
("posts.db", "posts_data", "Posts"),
("whatsapp.db", "whatsapp_data", "WhatsApp"),
("xiaohongshu.db", "xiaohongshu_data", "Xiaohongshu"),
("wechat.db", "wechat_data", "WeChat"),
]
CANDIDATE_AUTHORS = [
"author", "author_name", "username", "user_name", "user", "sender",
"nickname", "account", "screen_name", "reply_author", "comment_author", "name", "from"
]
CATEGORY_NAME = "Location, Transport & Environment"
ENV_SUBCATS = {"view", "nearby environment", "pest", "noise", "feng shui", "fengshui"}
def quote_ident(s):
s = s.replace('"', '""')
return f'"{s}"'
def classify_row(cat_raw, sub_raw, env_cat):
cat_clean = cat_raw.strip().lower()
sub_clean = sub_raw.strip().lower()
if env_cat.strip().lower() == cat_clean:
if sub_clean in ENV_SUBCATS:
return "Environment & View"
return "Location & Transport"
return cat_raw.strip()
def get_columns(con, table):
rows = con.execute(f"PRAGMA table_info({quote_ident(table)})").fetchall()
if not rows:
raise ValueError(f"Table {table} not found or has no columns.")
return [r[1] for r in rows]
def resolve_author_column(table_cols, override, source_label):
cols_lower = {c.lower(): c for c in table_cols}
if override:
override_lower = override.lower()
if override_lower in cols_lower:
return cols_lower[override_lower]
raise ValueError(
f"Specified author column '{override}' not found in table. "
f"Available columns: {', '.join(table_cols)}"
)
for cand in CANDIDATE_AUTHORS:
if cand in cols_lower:
return cols_lower[cand]
raise ValueError(
f"Could not auto-detect author column for source '{source_label}'. "
f"Available columns: {', '.join(table_cols)}"
)
def main():
parser = argparse.ArgumentParser(description="SQLite Sentiment Report")
parser.add_argument(
"--author-column",
action="append",
default=[],
help="Override author column in format SOURCE=COLUMN (e.g., posts.db=sender)"
)
parser.add_argument(
"--output",
type=str,
default="reply_author_counts.xlsx",
help="Output Excel filename (default: reply_author_counts.xlsx)"
)
parser.add_argument(
"--overwrite",
action="store_true",
help="Overwrite existing workbook if present"
)
args = parser.parse_args()
overrides = {}
for item in args.author_column:
if "=" not in item:
raise ValueError(f"Invalid override format '{item}', expected SOURCE=COLUMN")
src, col = item.split("=", 1)
overrides[src.strip()] = col.strip()
output_path = BASE_DIR / args.output
if output_path.exists() and not args.overwrite:
print(f"Error: Output file '{output_path}' already exists. Use --overwrite to replace it.")
sys.exit(1)
# Collect stats for all sources
# Structure: { source_label: { category: stats_dict } }
all_source_stats = {}
errors_occurred = []
for db_name, table_name, label in SOURCES:
db_path = DB_DIR / db_name
if not db_path.exists():
print(f"[{label}] Database file not found: {db_path}")
errors_occurred.append(f"[{label}] Database file not found: {db_path}")
print("-" * 80)
continue
try:
uri = f"file:{db_path.as_posix()}?mode=ro"
con = sqlite3.connect(uri, uri=True)
con.row_factory = sqlite3.Row
table_cols = get_columns(con, table_name)
required = ["cat", "sub_cat", "sentiment"]
cols_lower = {c.lower(): c for c in table_cols}
missing = [r for r in required if r not in cols_lower]
if missing:
raise ValueError(f"Missing required columns: {', '.join(missing)}. "
f"Available columns: {', '.join(table_cols)}")
col_cat = cols_lower["cat"]
col_sub = cols_lower["sub_cat"]
col_sent = cols_lower["sentiment"]
ov = overrides.get(db_name)
col_author = resolve_author_column(table_cols, ov, label)
q_cat = quote_ident(col_cat)
q_sub = quote_ident(col_sub)
q_sent = quote_ident(col_sent)
q_auth = quote_ident(col_author)
query = f"""
SELECT {q_cat} as cat, {q_sub} as sub_cat, {q_sent} as sent, {q_auth} as auth
FROM {quote_ident(table_name)}
"""
rows = con.execute(query).fetchall()
con.close()
except Exception as e:
print(f"[{label}] ERROR: {e}")
errors_occurred.append(f"[{label}] ERROR: {e}")
print("-" * 80)
continue
stats = {}
for row in rows:
cat_raw = row["cat"] or ""
sub_raw = row["sub_cat"] or ""
sent_raw = (row["sent"] or "").strip().lower()
auth_raw = (row["auth"] or "").strip().lower()
mapped_cat = classify_row(cat_raw, sub_raw, CATEGORY_NAME)
if mapped_cat not in stats:
stats[mapped_cat] = {
"total": 0,
"authors": set(),
"neg": 0, "neg_authors": set(),
"pos": 0, "pos_authors": set(),
"neu": 0, "neu_authors": set(),
}
bucket = stats[mapped_cat]
bucket["total"] += 1
if auth_raw:
bucket["authors"].add(auth_raw)
if sent_raw.startswith("neg"):
bucket["neg"] += 1
if auth_raw:
bucket["neg_authors"].add(auth_raw)
elif sent_raw.startswith("pos"):
bucket["pos"] += 1
if auth_raw:
bucket["pos_authors"].add(auth_raw)
elif sent_raw.startswith("neu"):
bucket["neu"] += 1
if auth_raw:
bucket["neu_authors"].add(auth_raw)
# Print terminal report for this source
print(f"Source: {label}")
print("-" * 80)
cat_w = 30
print(f"{'Category':<{cat_w}} | {'Total':>6} | {'Authors':>7} | {'Neg':>4} | {'NegAuth':>7} | {'Pos':>4} | {'PosAuth':>7} | {'Neu':>4} | {'NeuAuth':>7}")
for cat in sorted(stats.keys()):
b = stats[cat]
print(
f"{cat:<{cat_w}} | "
f"{b['total']:>6} | "
f"{len(b['authors']):>7} | "
f"{b['neg']:>4} | "
f"{len(b['neg_authors']):>7} | "
f"{b['pos']:>4} | "
f"{len(b['pos_authors']):>7} | "
f"{b['neu']:>4} | "
f"{len(b['neu_authors']):>7}"
)
print("-" * 80)
all_source_stats[label] = stats
# If any source failed, exit nonzero without saving
if errors_occurred:
print("\nOne or more sources failed. No incomplete workbook will be saved.")
sys.exit(1)
# Write Excel workbook
wb = openpyxl.Workbook()
# Remove default sheet
wb.remove(wb.active)
headers = ["Category", "Total Replies", "Authors", "Negative Replies", "Negative Authors", "Positive Replies", "Positive Authors", "Neutral Replies", "Neutral Authors"]
for db_name, table_name, label in SOURCES:
ws = wb.create_sheet(title=label)
ws.append(headers)
stats = all_source_stats.get(label, {})
for cat in sorted(stats.keys()):
b = stats[cat]
row_data = [
cat,
b["total"],
len(b["authors"]),
b["neg"],
len(b["neg_authors"]),
b["pos"],
len(b["pos_authors"]),
b["neu"],
len(b["neu_authors"]),
]
ws.append(row_data)
try:
wb.save(output_path)
print(f"Workbook saved to: {output_path}")
except Exception as e:
print(f"Error saving workbook: {e}")
sys.exit(1)
if __name__ == "__main__":
main()
|
Pastebin